Traffic shaping and Quality of Service (QoS) enforcement are critical for managing bandwidth, latency, and fairness in networks. These tasks often rely on low-level traffic control settings, which require manual setup and technical expertise. This paper presents an automated framework that converts high-level traffic shaping intents in natural or declarative language into valid and correct traffic control rules. To the best of our knowledge, we present the first end-to-end pipeline that ties intent translation in a queuing-theoretic semantic model and, with a rule-based critic, yields deployable Linux traffic control configuration sets. The framework has three steps: (1) a queuing simulation with priority scheduling and Active Queue Management (AQM) builds a semantic model; (2) a language model, using this semantic model and a traffic profile, generates sub-intents and configuration rules; and (3) a rule-based critic checks and adjusts the rules for correctness and policy compliance. We evaluate multiple language models by generating traffic control commands from business intents that comply with relevant standards for traffic control protocols. Experimental results on 100 intents show significant gains, with LLaMA3 reaching 0.88 semantic similarity and 0.87 semantic coverage, outperforming other models by over 30\. A thorough sensitivity study demonstrates that AQM-guided prompting reduces variability threefold compared to zero-shot baselines.

Service Function Chaining (SFC) requires efficient placement of Virtual Network Functions (VNFs) to satisfy diverse service requirements while maintaining high resource utilization in Data Centers (DCs). Conventional static resource allocation often leads to overprovisioning or underprovisioning due to the dynamic nature of traffic loads and application demands. To address this challenge, we propose a hybrid forecast-driven Deep reinforcement learning (DRL) framework that combines predictive intelligence with SFC provisioning. Specifically, we leverage DRL to generate datasets capturing DC resource utilization and service demands, which are then used to train deep learning forecasting models. Using Optuna-based hyperparameter optimization, the best-performing models, Spatio-Temporal Graph Neural Network, Temporal Graph Neural Network, and Long Short-Term Memory, are combined into an ensemble to enhance stability and accuracy. The ensemble predictions are integrated into the DC selection process, enabling proactive placement decisions that consider both current and future resource availability. Experimental results demonstrate that the proposed method not only sustains high acceptance ratios for resource-intensive services such as Cloud Gaming and VoIP but also significantly improves acceptance ratios for latency-critical categories such as Augmented Reality increases from 30% to 50%, while Industry 4.0 improves from 30% to 45%. Consequently, the prediction-based model achieves significantly lower E2E latencies of 20.5%, 23.8%, and 34.8% reductions for VoIP, Video Streaming, and Cloud Gaming, respectively. This strategy ensures more balanced resource allocation, and reduces contention.

Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventional approaches rely on transmitting raw video or high-dimensional sensory data from roadside units (RSUs) to vehicles, which is impractical under vehicular communication bandwidth and latency constraints. In this work, we propose a semantic V2X framework in which RSU-mounted cameras generate spatiotemporal semantic embeddings of future frames using the Video Joint Embedding Predictive Architecture (V-JEPA). To evaluate the system, we construct a digital twin of an urban traffic environment enabling the generation of d verse traffic scenarios with both safe and collision events. These embeddings of the future frame, extracted from V-JEPA, capture task-relevant traffic dynamics and are transmitted via V2X links to vehicles, where a lightweight attentive probe and classifier decode them to predict imminent collisions. By transmitting only semantic embeddings instead of raw frames, the proposed system significantly reduces communication overhead while maintaining predictive accuracy. Experimental results demonstrate that the framework with an appropriate processing method achieves a 10% F1-score improvement for collision prediction while reducing transmission requirements by four orders of magnitude compared to raw video. This validates the potential of semantic V2X communication to enable cooperative, real-time collision prediction in ITS.

Designing optimal non-terrestrial network (NTN) constellations is essential for maximizing throughput and ensuring fair resource distribution. This paper presents FTA-NTN (Fairness and Throughput Assurance in Non-Terrestrial Networks), a multi-objective optimization framework that jointly maximizes throughput and fairness under realistic system constraints. The framework integrates multi-layer Walker Delta constellations, a parametric mobility model for user distributions across Canadian land regions, adaptive K-Means clustering for beamforming and user association, and Bayesian optimization for parameter tuning. Simulation results with 500 users show that FTA-NTN achieves over 9.88 Gbps of aggregate throughput with an average fairness of 0.42, corresponding to an optimal configuration of 9 planes with 15 satellites per plane in LEO and 7 planes with 3 satellites per plane in MEO. These values align with 3GPP NTN evaluation scenarios and representative system assumptions, confirming their relevance for realistic deployments. Overall, FTA-NTN demonstrates that throughput and fairness can be jointly optimized under practical constraints, advancing beyond throughput-centric designs in the literature and offering a scalable methodology for next-generation NTN deployments that supports efficient and equitable global connectivity.

Effective Service Function Chain (SFC) provisioning requires precise orchestration in dynamic and latency-sensitive networks. Reinforcement Learning (RL) improves adaptability but often ignores structured domain knowledge, which limits generalization and interpretability. Large Language Models (LLMs) address this gap by translating natural language (NL) specifications into executable Structured Query Language (SQL) commands for specification-driven SFC management. Conventional fine-tuning, however, can cause syntactic inconsistencies and produce inefficient queries. To overcome this, we introduce Abstract Syntax Tree (AST)-Masking, a structure-aware fine-tuning method that uses SQL ASTs to assign weights to key components and enforce syntax-aware learning without adding inference overhead. Experiments show that AST-Masking significantly improves SQL generation accuracy across multiple language models. FLAN-T5 reaches an Execution Accuracy (EA) of 99.6%, while Gemma achieves the largest absolute gain from 7.5% to 72.0%. These results confirm the effectiveness of structure-aware fine-tuning in ensuring syntactically correct and efficient SQL generation for interpretable SFC orchestration.

This paper presents a Deep Hierarchical Reinforcement Learning (DHRL) framework for reliable task scheduling in MEC-enabled 5G Open RAN systems under on-off jamming attacks. The scheduling problem is modeled as a combinatorial integer nonlinear program (ComINP), which is hard to solve directly. To handle this, we use Deep Reinforcement Learning (DRL). Since the jamming environment is only partially observable, the problem becomes a Partially Observable Markov Decision Process (POMDP). To deal with this, we split the problem into two DRL agents. The first agent is a jamming estimator that uses an Alternating Discrete Phase-Type Renewal Process (ADPHRP) to predict jammed time slots based on dense distribution patterns. It is trained using a Proximal Policy Optimization (PPO) algorithm. The second agent is a task scheduler called Weighted MAC-based Task Scheduler (WMAC-TS), which schedules tasks during non-jammed slots while maintaining quality of service (QoS). It uses a transformer-based Actor-Critic model with linear complexity relative to the number of tasks, considering both short-term and long-term rewards. Simulation results show that the PPO-based jamming estimator achieves a cumulative prediction error of 13 time slots in 100 time slots, compared to 25 time slots for DDQN with historical data and 48 time slots for standard DDQN. For 50 active users, WMAC-TS achieves a task drop ratio of 0.917 lower than the 0.942 of the baseline genetic algorithm, and cuts execution time from 1260 seconds to 316 seconds.

In this paper, we propose a novel joint task offloading and user scheduling (JTO-US) framework for 5G mobile edge computing (MEC) systems under security threats from jamming attacks. The goal is to minimize the delay and the ratio of dropped tasks, taking into account both communication and computation delays. The system model includes a 5G network equipped with MEC servers and an adversarial on-off jammer that disrupts communication. The proposed framework optimally schedules tasks and users to minimize the impact of jamming while ensuring that high-priority tasks are processed efficiently. Genetic algorithm (GA) is used to solve the optimization problem, and the results are compared with benchmark methods such as GA without considering jamming effect, Shortest Job First (SJF), and Shortest Deadline First (SDF). The simulation results demonstrate that the proposed JTO-US framework achieves the lowest drop ratio in the presence of the jammer and effectively manages priority tasks, outperforming existing methods. Particularly, when the jamming probability is 0.8, the proposed framework mitigates the jammer's impact by reducing the drop ratio to 63%, compared to 89% achieved by the next best method.

In this paper, we tackle the challenge of jamming attacks in Ultra-Reliable Low Latency Communication (URLLC) within Non-Orthogonal Multiple Access (NOMA)-based 5G networks under Finite Blocklength (FBL) conditions. We introduce an innovative approach that employs Reconfigurable Intelligent Surfaces (RIS) with active elements to enhance energy efficiency while ensuring reliability and meeting latency requirements. Our approach incorporates the traffic model, making it practical for real-world scenarios with dynamic traffic loads. We thoroughly analyze the impact of blocklength and packet arrival rate on network performance metrics and investigate the optimal amplitude value and number of RIS elements. Our results indicate that increasing the number of RIS elements from 4 to 400 can improve signal-to-jamming-plus-noise ratio (SJNR) by 13.64 %. Additionally, optimizing blocklength and packet arrival rate can achieve a 31.68 % improvement in energy efficiency and reduced latency. These findings underscore the importance of optimized settings for effective jamming mitigation.

Cyber-security for 5G networks is drawing notable attention due to an increase in complex jamming attacks that could target the critical 5G Radio Frequency (RF) domain. These attacks pose a significant risk to heterogeneous network (HetNet) architectures, leading to degradation in network performance. Conventional machine-learning techniques for jamming detection rely on centralized training while increasing the odds of data privacy. To address these challenges, this paper proposes a decentralized two-stage federated learning (FL) framework for jamming detection in 5G femtocells. Our proposed distributed framework encompasses using the Federated Averaging (FedAVG) algorithm to train a Convolutional Autoencoder (CAE) for unsupervised learning. In the second stage, we use a fully connected network (FCN) built on the pre-trained CAE encoder that is trained using Federated Proximal (FedProx) algorithm to perform supervised classification. Our experimental results depict that our proposed framework (FedAVG and FedProx) accomplishes efficient training and prediction across non-IID client datasets without compromising data privacy. Specifically, our framework achieves a precision of 0.94, recall of 0.90, F1-score of 0.92, and an accuracy of 0.92, while minimizing communication rounds to 30 and achieving robust convergence in detecting jammed signals with an optimal client count of 6.

High-quality Service Function Chaining (SFC) provisioning is provided by the timely execution of Virtual Network Functions (VNFs) in a defined sequence. Advanced Deep Reinforcement Learning (DRL) solutions are utilized in many studies to contribute to fast and reliable autonomous SFC provisioning. However, under a large-scale network environment, centralized solutions might struggle to provide efficient outcomes when handling massive demands with stringent End-to-End (E2E) delay constraints. Therefore, in this paper, a novel distributed SFC provisioning framework is proposed, where the network is divided into several clusters. Each cluster has a dedicated local agent with a DRL module to handle the SFC provisioning of demands in that cluster. Also, there is a general agent that can communicate with local agents to handle the requests beyond their capacity. The DRL module of local agents can be applied under different configurations of clusters independent of different numbers of data centers and logical links in each cluster. Simulation results demonstrate that utilizing the proposed distributed framework offers up to 60 % improvements in the acceptance ratio of service requests in comparison to the centralized approach while minimizing the E2E delay of accepted requests.

Virtualization technology, Network Function Virtualization (NFV), gives flexibility to communication and 5G core network technologies for dynamic and efficient resource allocation while reducing the cost and dependability of the physical infrastructure. In the NFV context, Service Function Chain (SFC) refers to the ordered arrangement of various Virtual Network Functions (VNFs). To provide an automated SFC provisioning algorithm that satisfies high demands of SFC requests having ultra-reliable and low latency communication (URLLC) requirements, in the literature, Artificial Intelligence (AI) modules and Deep Reinforcement Learning (DRL) algorithms are investigated in detail. This research proposes a generative Variational Autoencoder (VAE) assisted advanced-DRL module for handling SFC requests in a dynamic environment where network configurations and request amounts can be changed. Using the hybrid approach, including generative VAE and DRL, the algorithm leverages several advantages, such as dimensionality reduction, better generalization on the VAE side, exploration, and trial-error learning from the DRL model. Results show that GenAI-assisted DRL surpasses the state-of-the-art model of DRL in SFC provisioning in terms of SFC acceptance ratio, E2E delay, and throughput maximization.

In critical situations such as natural disasters, network outages, battlefield communication, or large-scale public events, Unmanned Aerial Vehicles (UAVs) offer a promising approach to maximize wireless coverage for affected users in the shortest possible time. In this paper, we propose a novel framework where multiple UAVs are deployed with the objective to maximize the number of served user equipment (UEs) while ensuring a predefined data rate threshold. UEs are initially clustered using a K-means algorithm, and UAVs are optimally positioned based on the UEs’ spatial distribution. To optimize power allocation and mitigate inter-cluster interference, we employ the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, considering both LOS and NLOS fading. Simulation results demonstrate that our method significantly enhances UEs coverage and outperforms Deep Q-Network (DQN) and equal power distribution methods, improving their UE coverage by up to 2.07 times and 8.84 times, respectively.

In the ever-expanding domain of 5G-NR wireless cellular networks, over-the-air jamming attacks are prevalent as security attacks, compromising the quality of the received signal. We simulate a jamming environment by incorporating additive white Gaussian noise (AWGN) into the real-world In-phase and Quadrature (I/Q) OFDM datasets. A Convolutional Autoencoder (CAE) is exploited to implement a jamming detection over various characteristics such as heterogenous I/Q datasets; extracting relevant information on Synchronization Signal Blocks (SSBs), and fewer SSB observations with notable class imbalance. Given the characteristics of datasets, balanced datasets are acquired by employing a Conv1D conditional Wasserstein Generative Adversarial Network-Gradient Penalty(CWGAN-GP) on both majority and minority SSB observations. Additionally, we compare the performance and detection ability of the proposed CAE model on augmented datasets with benchmark models: Convolutional Denoising Autoencoder (CDAE) and Convolutional Sparse Autoencoder (CSAE). Despite the complexity of data heterogeneity involved across all datasets, CAE depicts the robustness in detection performance of jammed signal by achieving average values of 97.33% precision, 91.33% recall, 94.08% F1-score, and 94.35 % accuracy over CDAE and CSAE.

Real-time task processing is a critical challenge in vehicular networks, where achieving low latency and minimizing dropped task ratio depend on efficient task execution. Our primary objective is to maximize the number of completed tasks while minimizing overall latency, with a particular focus on reducing number of dropped tasks. To this end, we investigate both static and dynamic versions of an optimization algorithm. The static version assumes full task availability, while the dynamic version manages tasks as they arrive. We also distinguish between online and offline cases: the online version incorporates execution time into the offloading decision process, whereas the offline version excludes it, serving as a theoretical benchmark for optimal performance. We evaluate our proposed Online Dynamic Cost-Driven Algorithm (On-Dyn-CDA) against these baselines. Notably, the static Particle Swarm Optimization (PSO) baseline assumes all tasks are transferred to the RSU and processed by the MEC, and its offline version disregards execution time, making it infeasible for real-time applications despite its optimal performance in theory. Our novel On-Dyn-CDA completes execution in just 0.05 seconds under the most complex scenario, compared to 1330.05 seconds required by Dynamic PSO. It also outperforms Dynamic PSO by 3.42% in task loss and achieves a 29.22% reduction in average latency in complex scenarios. Furthermore, it requires neither a dataset nor a training phase, and its low computational complexity ensures efficiency and scalability in dynamic environments.

Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. However, open-source LLMs usually have more limitations regarding their performance, such as their arithmetic calculation and reasoning capacities, and practical systems of applying LLMs to IoT have yet to be well-explored. Therefore, we propose an LLM-based Generative IoT (GIoT) system deployed in the local network setting in this study. To alleviate the limitations of LLMs and provide service with competitive performance, we apply prompt engineering methods to enhance the capacities of the open-source LLMs, design a Prompt Management Module and a Postprocessing Module to manage the tailored prompts for different tasks and process the results generated by the LLMs. To demonstrate the effectiveness of the proposed system, we discuss a challenging table question answering (Table-QA) task as a case study of the proposed system, as tabular data is usually more challenging than plaintext because of their complex structures, heterogeneous data types and sometimes huge sizes. We conduct comprehensive experiments on the two popular Table-QA data sets, and the results show that our proposal can achieve competitive performance compared with state-of-the-art LLMs, demonstrating that the proposed LLM-based GIoT system can provide competitive performance with tailored prompting methods and is easily extensible to new tasks without training.

The convergence of Web 3.0 and Metaverse technologies with Connected Autonomous Vehicles (CAVs) is catalyzing a new era of intelligent vehicular systems, characterized by decentralization, immersive interaction, and enhanced autonomy. This paradigm is especially valuable in scenarios demanding secure peer-to-peer coordination, trustless automations, and seamless integration of physical and virtual environments under real-time constraints. Nonetheless, realizing such intelligent applications introduces critical challenges, including the development of robust decentralized governance and smart contracts, ensuring ultra-low-latency and high-throughput communications in edge computing contexts, achieving seamless digital–physical synchronization via high-fidelity digital twins or Metaverse representations, and guaranteeing scalability and privacy across distributed vehicle networks. This special issue brings together a collection of pioneering research that tackles these multifaceted challenges, showcasing innovations that advance the state of the art toward more secure, responsive, immersive, and decentralized CAV systems empowered by Web 3.0 and Metaverse technologies.

Multi-Access Edge Computing (MEC) is widely recognized as an essential enabler for applications that necessitate minimal latency. However, the dropped task ratio metric has not been studied thoroughly in literature. Neglecting this metric can potentially reduce the system’s capability to effectively manage tasks, leading to an increase in the number of eliminated or unprocessed tasks. This paper presents a 5G-MEC task offloading scenario with a focus on minimizing the dropped task ratio, computational latency, and communication latency. We employ Mixed Integer Linear Programming (MILP), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) to optimize the latency and dropped task ratio. We conduct an analysis on how the quantity of tasks and User Equipment (UE) impacts the ratio of dropped tasks and the latency. The tasks that are generated by UEs are classified into two categories: urgent tasks and non-urgent tasks. The UEs with urgent tasks are prioritized in processing to ensure a zero-dropped task ratio. Our proposed method improves the performance of the baseline methods, First Come First Serve (FCFS) and Shortest Task First (STF), in the context of 5G-MEC task offloading. Under the MILP-based approach, the latency is reduced by approximately 55% compared to GA and 35% compared to PSO. The dropped task ratio under the MILP-based approach is reduced by approximately 70% compared to GA and by 40% compared to PSO.

Machine Learning (ML) techniques have gained extensive attention for network intrusion detection. However, integrating ML approaches faces two primary challenges due to the presence of multi-class attacks and their varying impact levels on the network: the one-size-fits-all dilemma and the consideration of intrusion costs. Since ML models exhibit differing detection performances for each attack class, a single ML model may not suffice for predicting all attacks. Additionally, intrusion cost, a crucial concern for users and network service providers, is often overlooked in intrusion detection scheme development. To address these challenges, we propose a novel ensemble-learning framework called All Predict Cost Efficient Decides (APCED). APCED integrates multiple ML models, selecting an expert ML model for each attack class to minimize intrusion costs. In APCED, both damage cost and response cost determine the cost-efficient base estimators for ensemble learning, with an aggregation strategy employed for final decisions. We evaluate the performance of APCED using the NSL-KDD dataset. Numerical results demonstrate that APCED enhances the overall weighted F1 score by 81.13% compared to Adaboost and achieves an overall cost reduction of 54.7% and 87% compared to XGBoost and Adaboost, respectively.

In networks with limited resources, the concept of offloading computation to Mobile Edge Computing (MEC) has emerged as a promising research direction with the advent of new services in fifth-generation (5G) networks. However, poorly designed offloading strategies can lead to excessive energy consumption and unpredictable latency, while the number of dropped tasks significantly impacts system efficiency. This paper presents a 5G-MEC task offloading scenario aimed at minimizing computation and communication latency, energy consumption, and the rate of dropped tasks. To achieve this, we employ Mixed Integer non-Linear Programming (MINLP) and Mixed Integer Linear Programming (MILP), comparing their performance with Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Our analysis considers the impact of the quantity of tasks and User Equipment (UE) on network parameters, distinguishing between urgent and non-urgent tasks. We ensure a zero-dropped task rate for urgent tasks. The proposed approach outperforms baseline techniques such as First Come First Serve (FCFS), Shortest Deadline First (SDF), and Urgent Tasks First (UTF) in the context of 5G-MEC task offloading. Specifically, compared to MILP, PSO, and GA, the MINLP-based approach reduces total latency by 12%, 34%, and 44%, respectively. Moreover, it decreases energy consumption by 8%, 30%, and 47% compared to MILP, PSO, and GA, respectively. The dropped task ratio is also reduced by 17%, 42%, and 65% under the MINLP-based approach compared to MILP, PSO, and GA, respectively.

Service Function Chain (SFC) provisioning stands as a pivotal technology in the realm of 5G and future networks. Its essence lies in orchestrating VNFs (Virtual Network Functions) in a specified sequence for different types of SFC requests. Efficient SFC provisioning requires fast, reliable, and automatic VNFs’ placements, especially in a network where massive amounts of SFC requests are generated having ultrareliable and low latency communication (URLLC) requirements. Although much research has been done in this area, including Artificial Intelligence (AI) and Machine Learning (ML)-based solutions, this work presents an advanced Deep Reinforcement Learning (DRL)-based simulation model for SFC provisioning that illustrates a realistic environment. The proposed simulation platform can handle massive heterogeneous SFC requests having different characteristics in terms of VNFs chain, bandwidth, and latency constraints. Also, the model is flexible to apply to networks having different configurations in terms of the number of data centers (DCs), logical connections among DCs, and service demands. The simulation model components and the workflow of processing VNFs in the SFC requests are described in detail. Numerical results demonstrate that using this simulation setup and proposed algorithm, a realistic SFC provisioning can be achieved with an optimal SFC acceptance ratio while minimizing the E2E latency and resource consumption.

We propose Deep Dict, a deep learning-based lossy time series compressor designed to achieve a high compression ratio while maintaining decompression error within a predefined range. Deep Dict incorporates two essential components: the Bernoulli transformer autoencoder (BTAE) and a distortion constraint. BTAE extracts Bernoulli representations from time series data, reducing the size of the representations compared to conventional autoencoders. The distortion constraint limits the prediction error of BTAE to the desired range. More-over, in order to address the limitations of common regression losses such as L1/L2, we introduce a novel loss function called quantized entropy loss (QEL). QEL takes into account the specific characteristics of the problem, enhancing robustness to outliers and alleviating optimization challenges. Our evaluation of Deep Dict across diverse time series datasets from various IoT domains reveals that Deep Dict outperforms state-of-the-art lossy compressors in terms of compression ratio by a significant margin by up to 53.66%.

Jamming attacks present a crucial threat to the quality of service in wireless networks, disrupting essential features including reliability, latency, and effective rate specifically in mission-critical applications. This paper introduces and evaluates a NOMA-based model to improve the robustness of wireless networks against jamming attacks. To investigate and address the consequences of a reactive jammer in this context, its effect on substantial network metrics such as reliability, average transmission delay, and the effective sum rate (ESR) under finite blocklength transmissions are mathematically computed, taking by considering the detection probability of the jammer. Furthermore, the effect of UEs' allocated power and blocklength on the network metrics is explored. Contrary to the existing literature, results show that gNB can mitigate the impact of reactive jamming by decreasing transmit power, making the transmissions covert at the jammer side. Finally, an optimization problem is formulated to maximize the ESR under reliability, delay, and transmit power constraints. It is shown that by adjusting the allocated transmit power to UEs by gNB, the gNB can bypass the jammer effect to fulfill the 0.99999 reliability and the latency of 5ms without the need for packet re-transmission.

Multi-Access Edge Computing (MEC) emerged as a viable computing allocation method that facilitates offloading tasks to edge servers for efficient processing. The integration of MEC with 5G, referred to as 5G-MEC, provides real-time processing and data-driven decision-making in close proximity to the user. The 5G- MEC has gained significant recognition in task offloading as an essential tool for applications that require low delay. Nevertheless, few studies consider the dropped task ratio metric. Disregarding this metric might possibly undermine system efficiency. In this paper, the dropped task ratio and delay has been minimized in a realistic 5G- MEC task offloading scenario implemented in NS3. We utilize Mixed Integer Linear Programming (MILP) and Genetic Algorithm (GA) to optimize delay and dropped task ratio. We examined the effect of the number of tasks and users on the dropped task ratio and delay. Compared to two traditional offloading schemes, First Come First Serve (FCFS) and Shortest Task First (STF), our proposed method effectively works in 5G-MEC task offloading scenario. For MILP, the dropped task ratio and delay has been minimized by 20% and 2ms compared to GA.

Evaluating service connectivity of OpenWiFi to endusers calls for meticulous analysis of traffic patterns to identify any unusual behavior. This work proposes an automated approach to annotate the partially labeled OpenWiFi data more effectively, enabling discrimination of anomalous behavior from normal traffic behavior. Our framework comprises feature selection, semi-supervised learning (SSL), deep semi-supervised transfer learning (DSSTL), and K-Means clustering analysis for forecasting pseudo labels on unlabeled data, utilizing limited labeled information to extract relevant Key Performance Indicators (KPIs). We utilized one-dimensional convolutional neural network (1D-CNN) and Long Short-Term Memory (LSTM), enhanced by semi-supervised learning (SSL) and unsupervised K-Means to generate pseudo labels as anomaly or normal for unlabeled data. DSSTL involves domain adaptation by combining SSL, transfer learning, and K-Means clustering algorithm, thereby generalizing the forecasting quality of pseudo labels over conventional SSL and clustering approach. Our findings showcase DSSTL-based 1D-CNN with Mean Square Error (MSE) loss outperforms the analysis for SSL and DSSTL-based LSTM in acquiring pseudo labels for all proportions of unlabeled data, as indicated by Calinski and Harabasz (CH) score. It is noticeable that DSSTL-based 1D-CNN with MSE achieves a CH score that increases by 94% corresponding to 25% over 30% unlabeled samples, regardless of the increasing trend in CH score with an increase in proportions of unlabeled samples.

IoT binary classification tasks can benefit significantly from edge computing because it allows for real-time processing and decision-making. By gathering and processing data locally, edge devices can lower latency and enable quicker response times, which is beneficial for applications whose main aims are safety and security. Cell phone usage while driving is one of the worst scenarios that decreases traffic safety and causes accidents. A wide range of new applications and services could be possible with the convergence of IoT and cell phone detection in the car while in driving mode. Machine learning methods, which include the ability to track people and objects in realtime, increase public safety by identifying and preventing potential security threats and improve transportation system efficiency by streamlining traffic and easing congestion. Although object detection is the most common approach for cell phone detection, the binary classification approach has been proposed because of its fast processing ability and easy deployment on edge devices. The device, in consideration, incorporates an inside camera to gather driver image data to perform binary classification. After collecting images from edge devices, these data are prepared in detail in an IID (independently and identically distributed) manner for better training for deep learning models. After training, test results are obtained by interpolation and extrapolation analyses. Results show that interpolation accuracy increases by $1.1 \%$ and extrapolation accuracy increases by $16.5 \%$.

Network Intrusion Detection Systems (NIDS) have been extensively investigated by monitoring real network traffic and analyzing suspicious activities. However, there are limitations in detecting specific types of attacks with NIDS, such as Advanced Persistent Threats (APT). Additionally, NIDS is restricted in observing complete traffic information due to encrypted traffic or a lack of authority. To address these limitations, a Host-based Intrusion Detection system (HIDS) evaluates resources in the host, including logs, files, and folders, to identify APT attacks that routinely inject malicious files into victimized nodes. In this study, a hybrid network intrusion detection system that combines NIDS and HIDS is proposed to improve intrusion detection performance. The host data undergoes a Language Processing (NLP)-based Bidirectional Encoder Representations from Transformers (BERT) model from textual representation to a numerical one in order to process host data in a similar way to the network flow data through machine learning models. The feature flattening technique is applied to flatten two-dimensional host-based features that is provided by BERT into one-dimensional vectors so that host-based and network flow-based features can be processed by advanced Machine Learning (ML) models. In order to enhance HIDS effectiveness, a two-stage collaborative classifier is utilized, which applies two tiers of machine learning algorithms, binary and multi-class classifiers, to detect network intrusions. Once a binary classifier is used to detect benign samples to reduce the complexity of the original problem, the attack data are classified by a multi-class supervised learner to identify attack types. Hence, the overall performance of the two-stage collaborative model outperforms the baseline classifier, XGBoost. The proposed method is shown to generalize across two well-known datasets, CICIDS 2018 and NDSec-1. The performance of XGBoost, which represents conventional ML, is evaluated. Combining host and network features enhances attack detection performance (macro average F1 score) by 8.1% under the CICIDS 2018 dataset and 3.7% under the NDSec-1 dataset. Meanwhile, the two-stage collaborative classifier improves detection performance for most single classes, especially for DoS-LOIC-UDP and DoS-SlowHTTPTest, with improvements of 30.7% and 84.3%, respectively, when compared with the traditional ML models.

Timely response of Network Intrusion Detection Systems (NIDS) is constrained by the flow generation process which requires accumulation of network packets. This paper introduces Multivariate Time Series (MTS) early detection into NIDS to identify malicious flows prior to their arrival at target systems. With this in mind, we first propose a novel feature extractor, Time Series Network Flow Meter (TS-NFM), that represents network flow as MTS with explainable features, and a new benchmark dataset is created using TS-NFM and the meta-data of CICIDS2017, called SCVIC-TS-2022. Additionally, a new deep learning-based early detection model called Multi-Domain Transformer (MDT) is proposed, which incorporates the frequency domain into Transformer. This work further proposes a Multi-Domain Multi-Head Attention (MD-MHA) mechanism to improve the ability of MDT to extract better features. Based on the experimental results, the proposed methodology improves the earliness of the conventional NIDS (i.e., percentage of packets that are used for classification) by 5 ×104times and duration-based earliness (i.e., percentage of duration of the classified packets of a flow) by a factor of 60, resulting in a 84.1% macro F1 score (31% higher than Transformer) on SCVIC-TS-2022. Additionally, the proposed MDT outperforms the state-of-the-art early detection methods by 5% and 6% on ECG and Wafer datasets, respectively.

Massive amount of data transmission in vehicle-to-everything (V2X) settings lead to heavy utilization of communication channels. Furthermore, reliable connectivity and fast data transmission can be achieved by either re-engineering the network architecture or using efficient methods that alter data attributes, such as volume. This paper proposes a new method called Sequential Tracking along with an event-based distracted driving detection algorithm. Existing studies using machine learning models and object detection aim to detect distracted drivers and send their detection outcomes to the cloud or edge units. However, minimizing the data transmission or exchange overhead remains understudied. Therefore, the proposed Sequential Tracking method with an event-based algorithm is applied to distracted driving detection models to reduce the data transmission overhead due to false predictions, i.e., false positives or false negatives. Furthermore, the proposed method considers the camera's inference time and storage capacity since AI models are deployed to edge units for these kinds of tasks. Numerical results, with the inclusion of parameter tuning, confirm that the overall accuracy performance of the model can be improved from 87% to 91%. Moreover, following upon parameter-tuning, false predictions in the test dataset are eliminated, and the number of data points is reduced to less than one-tenth leading to significant traffic reduction between the edge unit and the cloud.

Performance degradation of OpenWiFi traffic is a significant problem while provisioning service to a dense area consisting of thousands of clients operating at the same time. Among various vulnerabilities of poor performance in Wireless Local Area Networks (WLANs), deviation of a traffic pattern from normal indicates probable presence of anomaly or outlier. Adoption of machine learning algorithms including unsupervised and supervised models, the complexity of detection of a anomalous traffic along with respective root cause is untangled with augmented machine learning to involve domain knowledge input. In this paper, to cope with unlabeled data in an OpenWiFi setting, the following systematic work flow is proposed to augment machine learning-based anomaly detection. First, a combination of two unsupervised clustering algorithms is used to segregate the anomalies from normal distribution of traffic. The anomalous instances are confirmed via domain knowledge input. Next, supervised models are trained to detect anomalies in a different domain (Wireless Sensor Networks) with labeled data. Following upon feature extraction to obtain the same number of dimensions in the OpenWiFi data as the labeled dataset, trained supervised classifiers are used to detect anomalies in the OpenWiFi system. Furthermore, the impact of oversampling methods have also been investigated. Through numerical results we show the impact of the proposed supervised models in terms of decision-making metrics and the shift in performances from the standpoint of imbalanced distribution of rare-class classification problem.

Conventional AI-based service flow remains a challenge for IoT-enabled devices since data collected by local clients is transferred to a centralized server, which contains a global machine learning (ML) model. However, this introduces privacy and security concerns for the clients, and federated Learning is positioned to overcome this problem where each client trains a local model with its local data and shares its model parameters with the centralized server instead of sharing data. Upon the receipt of all parameters, it aggregates these parameters and generates a new global model. Later this global model is distributed among the clients. Various aggregation methods have been published for increasing the global model's accuracy performance after aggregation. However, those new aggregation algorithms are not fully investigated under malicious and collaborated environments. A malicious environment is a scenario where malicious clients are present and can share parameters to degrade the aggregated model performance. On the other hand, the collaborative environment is another scenario in which some clients can share information with each other in order to collaborate. To tackle this issue, we investigate a new aggregation method called Score Based Aggregation (SBA) That aims to mitigate the impact of the model parameters from such malicious clients without keeping compromising the training accuracy. We compare our result to a baseline approach where the malicious client is varied from 20% to 50%. Numerical results suggest that the SBA aggregation helps the model maintain the convergence of accuracy at higher levels in comparison to the baseline approach.

IEEE 802.11be -Extremely High Throughput-, commercially known as Wireless-Fidelity (Wi-Fi) 7 is the newest IEEE 802.11 amendment that comes to address the increasingly throughput hungry services such as Ultra High Definition (4K/8K) Video and Virtual/Augmented Reality (VR/AR). To do so, IEEE 802.11be presents a set of novel features that will boost the Wi-Fi technology to its edge. Among them, Multi-Link Operation (MLO) devices are anticipated to become a reality, leaving Single-Link Operation (SLO) Wi-Fi in the past. To achieve superior throughput and very low latency, a careful design approach must be taken, on how the incoming traffic is distributed in MLO capable devices. In this paper, we present a Reinforcement Learning (RL) algorithm named Multi-Headed Recurrent Soft-Actor Critic (MH-RSAC) to distribute incoming traffic in 802.11be MLO capable networks. Moreover, we compare our results with two non-RL baselines previously proposed in the literature named: Single Link Less Congested Interface (SLCI) and Multi-Link Congestion-aware Load balancing at flow arrivals (MCAA). Simulation results reveal that the MH-RSAC algorithm is able to obtain gains in terms of Throughput Drop Ratio (TDR) up to 35.2% and 6% when compared with the SLCI and MCAA algorithms, respectively. Finally, we observed that our scheme is able to respond more efficiently to high throughput and dynamic traffic such as VR and Web Browsing (WB) when compared with the baselines. Results showed an improvement of the MH-RSAC scheme in terms of Flow Satisfaction (FS) of up to 25.6% and 6% over the the SCLI and MCAA algorithms.

Incorporating machine learning algorithms with Intrusion Detection System (IDS) can detect network intrusions without human intervention and aims for Zero Touch Networks (ZTN). In this research, an automatic network-based features and host-based features integrated intrusion detection scheme is presented to improve the performance of network attack detection under the SCVIC-CIDS-2021 dataset which is derived from the integration of network packets and host logs of the CSE-CIC-IDS2018 dataset. Auto-encoder (AE) and Gated Recurrent Unit (GRU) are utilized for feature derivation to overcome the dimensionality mismatch between network-based and host-based features. The knowledge-based Prior Knowledge Input (PKI) model is used to combine unsupervised extra knowledge with a pre-trained supervised model for the final classification results. The results of the experiment reveal that the integration of network-based and host-based features is effective and the PKI model improves the performance of the original ML classification algorithm as well. Under the test set, the maximum achievable macro average F1-score reaches up to 97.08% which points out approximately 9% improvement compared to the best baseline performance.

Optical Character Recognition (OCR) tools have been widely used to extract text content from images in many applications including Information and Communications Technology (ICT) supply chains. Due to the characteristics of datasheets in global ICT supply chains, models trained with popular public datasets often suffer from domain adaptation problems. First, popular open source text recognition datasets do not contain all the characters and symbols that appear in the ICT documents, meaning that models trained with these datasets cannot recognize these special characters and symbols. Second, these datasets also do not contain the samples with multiple words and multiple lines assuming that there is an Text Detection model that can extract text areas perfectly, which is not practical for ICT documents. Besides, as far as we know, there is no open-source dataset specifically designed that can be used to evaluate the OCR tools in the ICT domain. Therefore, in this study, we first build a benchmark dataset for the text recognition problem in the ICT domain, which includes the special characters and symbols in the ICT domain, and samples with multiple lines and multiple words. Then we propose a novel multi-modal sequence-to-sequence model, which not only take images as input but also their corresponding their texts generated by a pre-trained model. We conducted extensive experiments to evaluate the proposed multi-modal method on the proposed dataset, and the empirical results show that the proposed method can recognize special characters and symbols, samples with multiple lines and multiple words, outperform benchmark models consistently.

Dense and unplanned IEEE 802.11 Wireless Fidelity (Wi-Fi) deployments and the continuous increase of throughput and latency stringent services for users have led to machine learning algorithms to be considered as promising techniques in the industry and the academia. Specifically, the ongoing IEEE 802.11be EHT —Extremely High Throughput, known as Wi-Fi 7— amendment propose, for the first time, Multi-Link Operation (MLO). Among others, this new feature will increase the complexity of channel selection due the novel multiple interfaces proposal. In this paper, we present a Parallel Transfer Reinforcement Learning (PTRL)-based cooperative Multi-Agent Reinforcement Learning (MARL) algorithm named Parallel Transfer Reinforcement Learning Optimistic-Weighted Value Decomposition Networks (oVDN) to improve intelligent channel selection in IEEE 802.11be MLO-capable networks. Additionally, we compare the impact of different parallel transfer learning alternatives and a centralized non-transfer MARL baseline. Two PTRL methods are presented: Multi-Agent System (MAS) Joint Q-function Transfer, where the joint Q-function is transferred and MAS Best/Worst Experience Transfer where the best and worst experiences are transferred among MASs. Simulation results show that oVDNg–only the best experiences are utilized– is the best algorithm variant. Moreover, oVDNgoffers a gain up to 3%, 7.2% and 11% when compared with VDN, VDN-nonQ and non-PTRL baselines. Furthermore, oVDNgexperienced a reward convergence gain in the 5 GHz interface of 33.3% over oVDNband oVDN where only worst and both types of experiences are considered, respectively. Finally, our best PTRL alternative showed an improvement over the non-PTRL baseline in terms of speed of convergence up to 40 episodes and reward up to 135%.

With the notable interest in unmanned aerial vehicle (UAV)-to-ground communications, new fading channel models that take into account the effects of shadowing have been proposed for beyond 5G networks. Guaranteeing physical layer security of the UAV-to-ground channels is essential for the transmission of confidential messages in the presence of an eavesdropper. In this paper, we examine physical layer security metrics, such as the average secrecy capacity, the secrecy outage probability, and the probability of strictly positive secrecy capacity, in UAV-to-ground communications with shadowing. Monte Carlo simulations are performed to verify the analytical expressions. Finally, the effect of the fading parameters on the system performance is studied.

Mobile crowdsensing (MCS) has become a prominent paradigm to collect and share data based on sensing devices with built-in sensors in the Internet of Things era. Nevertheless, conventional MCS confronts various security and privacy vulnerabilities in terms of decentralized, openness, and non-dedicated properties. Currently, the submitted tasks are collected and managed conventionally by a centralized MCS platform. A centralized MCS platform is not safe enough to protect and prevent tampering sensing tasks since it confronts the single point of failure, which reduces the effectiveness and robustness of the MCS system. Meanwhile, fake task attack is a serious threat, as it would drain excessive resources from the participant devices and clog the MCS servers to disrupt the services offered by the MCS. To address the centralized issue and identify fake tasks, a blockchain-based decentralized MCS is designed. Integration of blockchain into MCS enables a decentralized framework. Moreover, the distributed nature of a blockchain chain prevents sensing tasks from being tampered. The blockchain uses a practical Byzantine fault tolerance consensus that can tolerate one-third faulty nodes, making the implemented MCS system robust and sturdy. In addition, an ensemble learning approach is deployed in the blockchain for eliminating fake tasks by malicious requesters. The evaluation test is conducted under two different datasets representing a big city and a small one to have an MCS campaign. Numerical results show that the ensemble approach eliminates most of the fake tasks with a detection accuracy of up to 0.99. Furthermore, the ensemble learning integrated system outperforms individual learner based centralized systems, and non-fault tolerant systems in terms of Ratio of Legitimate Tasks (RoLT) saved and Ratio of Fake Tasks (RoFT).RoFTis low to 0.01, andRoLTis high up to 0.913 via the proposed MCS blockchain-driven framework.

In Mobile Crowdsensing (MCS), fake tasks can drain significant amount of resources. This paper proposes a new methodology to determine a proper time window for the training dataset and the impact of the accuracy of task legitimacy detection on the MCS campaign performance. To reach the desired performance, the task legitimacy detection is utilized in such a way that while legitimate tasks are kept, the fake tasks are eliminated as much as possible in the MCS platform through machine learning (ML) prediction. The proposed methodology is evaluated for legitimacy detection under multiple ML methods. Moreover, a knowledge-based fake task detection technique with effective feature selection is formulated to ensure fake tasks are filtered at the MCS servers. Detection accuracy is improved by using shorter time frame in training and longer time frame in prediction. The overall performance improvement based on profit, cost, legitimate tasks loss ratio, and fake tasks elimination ratio has been achieved under three different sizes of training datasets to verify the efficiency of the proposed methodology. Moreover, Prior Knowledge Input with Self-Organizing Feature Map outperforms the conventional legitimacy detection by 5.48%, 12.11% and 58.05% in terms of test accuracy, profit and cost under the small dataset, respectively.

The Internet of Things revolutionizes human life by inaugurating scenarios such as smart homes. However, IoT devices contain much sensitive information about users and devices from a security and privacy perspective. Through traffic-based attacks, adversaries map changes in traffic rates to a particular in-home user’s actions. An efficient IoT data instrumentation may protect users against traffic-based attacks by giving valuable information to adaptive network security solutions. Nonetheless, no work performs data instrumentation or uses feature exploration to reveal relevant features to assist network security management. Thus, this article introduces IoTReGuard, an IoT Method to Reveal and Guard IoT Network Traffic Features. IoTReguard aims to explore network traffic features to reveal the most relevant ones and hide them to protect users’ privacy. By IoT network feature exploration and data instrumentation, IoTReGuard provides valuable information on network traffic features to mask critical features. Results showed that IoTReGuard reduced from 70% to 20% of F1-Score on identifying the IoT devices, improving user privacy.

Intrusion Detection Systems (IDS) are critical secu-rity mechanisms that protect against a wide variety of network threats and malicious behaviors on networks or hosts. As both Network-based IDS (NIDS) or Host-based IDS (HIDS) have been widely investigated, this paper aims to present a Combined Intrusion Detection System (CIDS) that integrates network and host data in order to improve IDS performance. Due to the scarcity of datasets that include both network packet and host data, we present a novel CIDS dataset formation framework that can handle log files from a variety of operating systems and align log entities with network flows. A new CIDS dataset named SCVIC-CIDS-2021 is derived from the meta-data from the well-known benchmark dataset, CIC-IDS-2018 by utilizing the proposed framework. Furthermore, a transformer-based deep learning model named CIDS-Net is proposed that can take network flow and host features as inputs and outperform baseline models that rely on network flow features only. Experimental results to evaluate the proposed CIDS-Net under the SCVIC-CIDS-2021 dataset support the hypothesis for the benefits of combining host and flow features as the proposed CIDS- N et can improve the macro F1 score of baseline solutions by 6.36 % (up to 99.89%).

In this paper, we study the expanding attack surface of Adversarial Machine Learning (AML) and the potential attacks against Vehicle-to-Microgrid (V2M) services. We present an anticipatory study of a multi-stage gray-box attack that can achieve a comparable result to a white-box attack. Adversaries aim to deceive the targeted Machine Learning (ML) classifier at the network edge to misclassify the incoming energy requests from microgrids. With an inference attack, an adversary can collect real-time data from the communication between smart microgrids and a 5G gNodeB to train a surrogate (i.e., shadow) model of the targeted classifier at the edge. To anticipate the associated impact of an adversary's capability to collect real-time data instances, we study five different cases, each representing different amounts of real-time data instances collected by an adversary. Out of six ML models trained on the complete dataset, K-Nearest Neighbour (K-NN) is selected as the surrogate model, and through simulations, we demonstrate that the multi-stage gray-box attack is able to mislead the ML classifier and cause an Evasion Increase Rate (EIR) up to 73.2% using 40% less data than what a white-box attack needs to achieve a similar EIR.

The number of Internet of Things (IoT) devices being deployed into networks is growing at a phenomenal pace, which makes IoT networks more vulnerable in the wireless medium. Advanced Persistent Threat (APT) is malicious to most of the network facilities and the available attack data for training the machine learning-based Intrusion Detection System (IDS) is limited when compared to the normal traffic. Therefore, it is quite challenging to enhance the detection performance in order to mitigate the influence of APT. Therefore, Prior Knowledge Input (PKI) models are proposed and tested using the SCVIC-APT-2021 dataset. To obtain prior knowledge, the proposed PKI model pre-classifies the original dataset with unsupervised clustering method. Then, the obtained prior knowledge is incorporated into the supervised model to decrease training complexity and assist the supervised model in determining the optimal mapping between the raw data and true labels. The experimental findings indicate that the PKI model outperforms the supervised baseline, with the best macro average F1-score of 81.37%, which is 10.47% higher than the baseline.

The global Information and Communications Technology (ICT) supply chain is a complex network consisting of all types of participants. It is often formulated as a Social Network to discuss the supply chain network's relations, properties, and development in supply chain management. Information sharing plays a crucial role in improving the efficiency of the supply chain, and datasheets are the most common data format to describe e-component commodities in the ICT supply chain because of human readability. However, with the surging number of electronic documents, it has been far beyond the capacity of human readers, and it is also challenging to process tabular data automatically because of the complex table structures and heterogeneous layouts. Table Structure Recognition (TSR) aims to represent tables with complex structures in a machine-interpretable format so that the tabular data can be processed automatically. In this paper, we formulate TSR as an object detection problem and propose to generate an intuitive representation of a complex table structure to enable structuring of the tabular data related to the commodities. To cope with border-less and small layouts, we propose a cost-sensitive loss function by considering the detection difficulty of each class. Besides, we propose a novel anchor generation method using the character of tables that columns in a table should share an identical height, and rows in a table should share the same width. We implement our proposed method based on Faster-RCNN and achieve 94.79% on mean Average Precision (AP), and consistently improve more than 1.5% AP for different benchmark models.

Due to the characteristics of Information and Communications Technology (ICT) products, the critical information of ICT devices is often summarized in big tabular data shared across supply chains. Therefore, it is critical to automatically interpret tabular structures with the surging amount of electronic assets. To transform the tabular data in electronic documents into a machine-interpretable format and provide layout and semantic information for information extraction and interpretation, we define a Table Structure Recognition (TSR) task and a Table Cell Type Classification (CTC) task. We use a graph to represent complex table structures for the TSR task. Meanwhile, table cells are categorized into three groups based on their functional roles for the CTC task, namely Header, Attribute, and Data. Subsequently, we propose a multi-task model to solve the defined two tasks simultaneously by using the text modal and image modal features. Our experimental results show that our proposed method can outperform state-of-the-art methods on ICDAR2013 and UNLV datasets.

Mobile Crowdsensing systems are vulnerable to various attacks as they build on non-dedicated and ubiquitous properties. Machine learning (ML)-based approaches are widely investigated to build attack detection systems and ensure MCS systems security. However, adversaries that aim to clog the sensing front-end and MCS back-end leverage intelligent techniques, which are challenging for MCS platform and service providers to develop appropriate detection frameworks against these attacks. Generative Adversarial Networks (GANs) have been applied to generate synthetic samples, that are extremely similar to the real ones, deceiving classifiers such that the synthetic samples are indistinguishable from the originals. Previous works suggest that GAN-based attacks exhibit more crucial devastation than empirically designed attack samples, and result in low detection rate at the MCS platform. With this in mind, this paper aims to detect intelligently designed illegitimate sensing service requests by integrating a GAN-based model. To this end, we propose a two-level cascading classifier that combines the GAN discriminator with a binary classifier to prevent adversarial fake tasks. Through simulations, we compare our results to a single-level binary classifier, and the numeric results show that proposed approach raises Adversarial Attack Detection Rate (AADR), from 0% to 97.5% by KNN/NB, from 45.9% to 100% by Decision Tree. Meanwhile, with two-levels classifiers, Original Attack Detection Rate (OADR) improves for the three binary classifiers, with comparison, such as NB from 26.1% to 61.5%.

Mobile Crowdsensing (MCS) is a sensing paradigm that has transformed the way that various service providers collect, process, and analyze data. MCS offers novel processes where data is sensed and shared through mobile devices of the users to support various applications and services for cutting-edge technologies. However, various threats, such as data poisoning, clogging task attacks and fake sensing tasks adversely affect the performance of MCS systems, especially their sensing, and computational capacities. Since fake sensing task submissions aim at the successful completion of the legitimate tasks and mobile device resources, they also drain MCS platform resources. In this work, Self Organizing Feature Map (SOFM), an artificial neural network that is trained in an unsupervised manner, is utilized to pre-cluster the legitimate data in the dataset, thus fake tasks can be detected more effectively through less imbalanced data where legitimate/fake tasks ratio is lower in the new dataset. After pre-clustered legitimate tasks are separated from the original dataset, the remaining dataset is used to train a Deep Neural Network (DeepNN) to reach the ultimate performance goal. Pre-clustered legitimate tasks are appended to the positive prediction outputs of DeepNN to boost the performance of the proposed technique, which we refer to as pre-clustered DeepNN (PrecDeepNN). The results prove that the initial average accuracy to discriminate the legitimate and fake tasks obtained from DeepNN with the selected set of features can be improved up to an average accuracy of 0.9812 obtained from the proposed machine learning technique.

Energy-aware data collection is of paramount importance for robotic and wireless sensor networks. Although static sink-aided cluster-based protocols provide energy-efficient solutions, unmanned aerial vehicle (UAV)-aided approaches can be considered as better alternatives to reduce energy consumption while data acquisition compared with static sinks. Most of the existing UAV-driven solutions have not considered a limit on the battery capacity of the UAV, which needs to be considered in a practical manner. This article investigates energy-aware data collection in robot network clusters. In each cluster, a cluster head (CH) robot allocates one collaborative task to each cluster member (CM) robot and collects data from CMs whereas a UAV collects data from CH robots by visiting a subset of them due to its battery limitation. To complement the state-of-the-art, UAV decision for visiting the subset of CHs is constrained to multiple factors including residual battery capacity, as well as locations and data qualities of all CH robots. Nonvisited CH robots use CH robots as relay nodes for data forwarding. Following upon this, by considering the problem under data hopping constraints, this article also presents a sensitivity analysis with respect to data hopping constraints. Simulations show that the proposed policy achieves zero total joint cost whereas the state-of-the-art approaches result in significantly high total joint costs. Furthermore, the proposed policy reduces the total joint cost by up to 50% with respect to the conventional approaches.

Internet of things (IoT) networks confront vari-ous network intrusion threats due to massively interconnected nodes that form an extensive attack surface for adversaries. Machine learning (ML)-based approaches are widely investigated to address network intrusions. It becomes further challenging to achieve promising performance for multi-class classification so to identify each attack type rather than detection of the presence of intrusion, which involves binary classification. ML models perform divergent detection performance in each class, so it is challenging to select one ML model applicable to all classes prediction. With this in mind, we propose an innovative ensemble learning framework, namely All Predict Wisest Decides (APWD) that builds on training of multiple ML models and testing them independently so to obtain prediction performance for all classes. For each attack category, an expert (i.e., wisest) model that performs the best F1 score, accuracy, lowest false detection rate is determined according to individual model results. The aggregation module makes decisions relying upon the wisest model determined for each class. APWD is a generic framework, and the types of MLs and the number of MLs can be customized in APWD. Experiments under a popular public dataset, NSL-KDD verify the proposed approach APWD by demonstrating that APWD boosts overall accuracy to 0.797, comparing 0.772 by XGBoost, 0.758 by RF, and 0.584 by Adaboost. Moreover, in certain attack types R2L, APWD increases F1 score by a factor of 18, from 0.022 by RF to 0.421.

Mobile crowdsensing (MCS) leverages distributed and non-dedicated sensing concepts by utilizing sensors embedded in a large number of mobile smart devices. However, the openness and distributed nature of MCS leads to various vulnerabilities and consequent challenges to address. A malicious user submitting fake sensing tasks to an MCS platform may be attempting to consume resources from any number of participants’ devices; as well as attempting to clog the MCS server. In this paper, a novel approach that is based on horizontal federated learning is proposed to identify fake tasks that contain a number of independent detection devices and an aggregation entity. Detection devices are deployed to operate in parallel with each device equipped with a machine learning (ML) module, and an associated training dataset. Furthermore, the aggregation module collects the prediction results from individual devices and determines the final decision with the objective of minimizing the prediction loss. Loss measurement considers the lost task values with respect to misclassification, where the final decision utilizes a risk-aware approach where the risk is formulated as a function of the utility loss. Experimental results demonstrate that using federated learning-driven illegitimate task detection with a risk aware aggregation function improves the detection performance of the traditional centralized framework. Furthermore, the higher performance of detection and lower loss of utility can be achieved by the proposed framework. This scheme can even achieve 100% detection accuracy using small training datasets distributed across devices, while achieving slightly over an 8% increase in detection improvement over traditional approaches.

Precision in event characterization in connected vehicles has become increasingly important with the responsive connectivity that is available to modern vehicles. Event characterization via vehicular sensors is utilized in safety and autonomous driving applications in vehicles. While characterization systems are capable of predicting risky driving patterns, the precision of such systems remains an open issue. The major issues against the driving event characterization systems need to be addressed in connected vehicle settings, which are the heavy imbalance and the event infrequency of the driving data and the existence of the time-series detection systems that are optimized for vehicular settings. To overcome the problems, we introduce the application of the prior-knowledge input method to the characterization systems. Furthermore, we propose a recurrent-based denoising auto-encoder network to populate the existing data for a more robust training process. The results of the conducted experiments show that the introduction of knowledge-based modeling enables the existing systems to reach significantly higher accuracy and F1-score levels. Ultimately, the combination of the two methods enables the proposed model to attain a 14.7% accuracy boost over the baseline by achieving an accuracy of 0.96.

Federated Learning (FL) builds on a mobile network of participating nodes that train local models and contribute to the learning model parameters at a central server without being obliged to share their raw data. The server aggregates the uploaded model parameters to generate a global model. Common practice for the uploaded local models is an evenly weighted aggregation, assuming that each node of the network contributes to advancing the global model equally. Due to the heterogeneous nature of the devices and collected data, it is inevitable to have variations between the contributions of the users to the global model. Therefore, users (i.e., devices) with higher contributions should be weighted higher during aggregation. With this in mind, this paper proposes a reputation-enabled aggregation methodology that scales the aggregation weights of users by their reputation scores. Reputation score of a user is computed according to the performance metrics of their trained local models during each training round, therefore it can be a metric to evaluate the direct contributions of their trained local model. Numerical comparison of the proposed aggregation methodology to a baseline that utilizes standard averaging as well as a second baseline that is scoped to a reputation-based client selection shows an improvement of 17.175% over the standard baseline for not independent and identically distributed (non-IID) scenarios for an FL network of 100 participants. Consistent improvements over the first and second baselines under smaller FL networks with users ranging from 20 to 100 are also shown.

Mobile crowdsensing (MCS) has emerged as a ubiquitous solution for data collection from embedded sensors of smart devices to improve the sensing capacity and reduce sensing costs in large regions. Due to the ubiquitous nature of MCS services, smart devices require awareness of against misbehaving users that are becoming smarter to clog the resources in such a nondedicated sensing environment. In an MCS setting, the primary goal of a fake sensing task submission is to keep participant devices occupied, such as the battery, sensing, storage, and computing. Since the development of robust sensing campaigns highly depends on the existence of a realistic model of misbehaving users, this article leverages artificial intelligence and introduces a region-based self-organizing feature map (SOFM)-based model on user movement patterns so as to place the fake sensing tasks with the objective of maximum impacted participants and recruits. Uniformly and randomly initialized neurons are designed with fixed and adaptive quantities that are determined based upon the affected area on the covered terrain. Through numerical studies, we show that the impact of the SOFM structures can affect up to 46% of the participants and up to 37% of the recruits under various SOFM topologies. Furthermore, SOFM-based task submission models can increase the energy consumption in recruited devices by up to 39% due to the illegitimate task submission.

Volunteer computing uses Internet-connected devices (laptops, PCs, smart devices, etc.), in which their owners volunteer them as storage and computing power resources, has become an essential mechanism for resource management in numerous applications. The growth of the volume and variety of data traffic on the Internet leads to concerns on the robustness of cyberphysical systems especially for critical infrastructures. Therefore, the implementation of an efficient Intrusion Detection System for gathering such sensory data has gained vital importance. In this article, we present a comparative study of Artificial Intelligence (AI)-driven intrusion detection systems for wirelessly connected sensors that track crucial applications. Specifically, we present an in-depth analysis of the use of machine learning, deep learning and reinforcement learning solutions to recognise intrusive behavior in the collected traffic. We evaluate the proposed mechanisms by using KDD’99 as real attack dataset in our simulations. Results present the performance metrics for three different IDSs, namely the Adaptively Supervised and Clustered Hybrid IDS (ASCH-IDS), Restricted Boltzmann Machine-based Clustered IDS (RBC-IDS), and Q-learning based IDS (Q-IDS), to detect malicious behaviors. We also present the performance of different reinforcement learning techniques such as State-Action-Reward-State-Action Learning (SARSA) and the Temporal Difference learning (TD). Through simulations, we show that Q-IDS performs with detection rate while SARSA-IDS and TD-IDS perform at the order of .

Social networking research has primarily focused on public social networking services and applications, while rich social interactions in an enterprise setting and their related context has received less attention. In this paper, we focus on using the enterprise social context to augment traditional authentication tools. This is motivated by the emergence of smart mobile devices which introduce ease of remote access to work from almost anywhere and anytime, adding spatio-temporal dimension to the social context. However, it remains a challenge to efficiently manage access-controlled events by using different contextual properties. This paper analyzes specific actions under specific access-control rules to extract context-aware machine learning predictions. Such analysis includes the introduction of three contextual metrics: document shareability, valuation, and user cooperation. Furthermore, these socially-dependent metrics are combined with our Smart Enterprise Access Control (SEAC) technique to achieve authenticity precision of 99% while improving the corresponding efficiency trade-off associated with high and strict security.

Mobile crowdsensing (MCS) is a distributed sensing concept that enables ubiquitous sensing services via various builtin sensors in smart devices. However, MCS systems are vulnerable because of being non-dedicated. Especially, submission of fake tasks with the aim of clogging participants device resources as well as MCS servers is a crucial threat to MCS platforms. In this paper, we propose an ensemble learning-based solution for MCS platforms to mitigate illegitimate tasks. Furthermore, we also integrate k-means-based classification with the proposed method to extract region-specific features as input to the machine learningbased fake task detection. Through simulations, we compare the ensemble method to a previously proposed Deep Belief Network (DBN)-based fake task detection, which is also shown to improve performance in terms of accuracy, F1 score, recall, precision and geometric mean score (G-mean) with the integration of regionawareness. Our validation results show that the ensemble machine learning-based detection can eliminate majority of the fake tasks, with up to 0.995 precision, 0.997 recall, 0.996 F1, 0.993 accuracy and 0.982 G-Mean. Furthermore, the proposed solution introduces savings up to 12.18% battery of mobile devices while reducing the impacted recruits to 0.25% and protecting up to 10.59% participants against malicious sensing tasks.

Mobile Crowdsensing (MCS) builds on the Sensing as a Service model, and is considered to be an integral component of the Internet of Things systems. Since MCS does not build on a thoroughly assessed and established trust mechanism between all parties various threats including data poisoning, fake sensing tasks and clogging task attacks remain challenges. Fake task submissions are the least investigated although they have the potential to drain significant amount of resources (e.g. battery, sensors, processing, storage) and clog the MCS servers. This paper proposes a knowledge-based technique alongside sequential feature selection methodology to detect fake sensing tasks submitted to the MCS servers so that the tasks do not get assigned to the participants but filtered at the MCS servers. The proposed methodology is compared to fake task detection under Knowledge Based Deep Neural Network which is also enhanced by feature selection, and the simulation results show that the proposed methodology, by utilizing Deep Prior Knowledge Input with Self-Organizing Feature Map can outperform the deep neural network-based detection by 9.7% in terms of accuracy.

Mobile crowdsensing (MCS) is a ubiquitous sensing paradigm that emerged in the form of”sensed data as a service” model in the Internet of Things Era. Distributed nature of MCS results in vulnerabilities at the MCS platforms as well as participating devices that provide sensory data services. Submission of fake tasks with the aim of clogging sensing server resources and draining participating device batteries is a crucial threat that has not been investigated well. In this paper, we provide a detailed analysis by modeling a deep belief network (DBN) when the available sensory data is scarce for analysis. With oversampling to cope with the class imbalance challenge, a Principal Component Analysis (PCA) module is implemented prior to the DBN and weights of various features of sensing tasks are analyzed under varying inputs. The experimental results show that the presented DBN-driven fake task mitigation detection of fake sensing tasks can ensure up to 0.92 accuracy, 0.943 precision and up to 0.928 F1 score outperforming prior work on MCS data with deep learning networks.

With the increase of cyber attack risks on critical infrastructures monitored by networked systems, robust Intrusion Detection Systems (IDSs) for protecting the information have become vital. Designing an IDS that performs with maximum accuracy with minimum false alarms is a challenging task. Ensemble method considered as one of the main developments in machine learning in the past decade, it finds an accurate classifier by combining many classifiers. In this paper, an ensemble classification procedure is proposed using Random Forest (RF), DensityBased Spatial Clustering of Applications with Noise (DBSCAN) and Restricted Boltzmann Machine (RBM) as base classifiers. RF, DBSCAN, and RBM techniques have been used for classification purposes. The ensemble model is introduced for achieving better results. Bayesian Combination Classification (BCC) has been adopted as a combination technique. Independent BCC (IBCC) and Dependent BCC (DBCC) have been tested for performance comparison. The model shows a promising result for all classes of attacks. DBCC performs over IBCC in terms of accuracy and detection rates. Through simulations under a wireless sensor network scenario, we have verified that DBCC-based IDS works with ≈ 100% detection and ≈ 1.0 accuracy rate in the existence of intrusive behavior in the tested Wireless Sensor Network (WSN).

Non-dedicated nature of mobile crowdsensing (MCS) systems introduces vulnerabilities for MCS platforms in terms of sensing, computing, storage, and battery resources. The advent of adversarial artificial intelligence (AI) leads to high impact malicious behavior when adversaries aim to clog the resources of such a non-dedicated and ubiquitous system. This paper proposes an ensemble learning-based methodology for MCS platforms in order to mitigate the impacts of adversarial AI-driven fake task submission attacks, which are intelligently designed so to clog resources such as batteries, sensing, or memory resources. We validate our proposal through realistic simulations to generate crowdsensing data under two different cities, and intelligent fake task submissions under adversarial self-organizing maps. The experimental results show that when the submitted tasks undergo a Gradient Boosting-based classifier prior to being assigned to participants, the proposed solution can introduce battery savings at the participant devices up to 23%, and the impacted recruit population can be reduced from 24% to 6% whereas the defense mechanism can achieve an overall accuracy level above 98% concerning the legitimacy of the submitted tasks.

Documents are constantly being processed within supply chains in various industries throughout the globe. Within those documents, often times the most important content is stored in tabular format. Therefore an automated technique for supply chain document processing is highly desired. Deep learning approaches show promise to deliver an end-to-end extraction model. However, it has been shown that tabular detection accuracy is not always correlated to tabular localization accuracy. Portions of the desired tabular information can easily be cropped out due to a lack of localization accuracy. In this paper, we propose a two stage convolutional neural network-based deep learning framework to improve tabular localization accuracy. We use pre-trained backbone network ResNet-50 and then apply transfer learning to fit our application. One of our main contributions is the introduction of the KL loss function into Faster-RCNN. Once the bounding box variances are acquired from the KL loss function, we introduce a voting procedure with soft-non-maximum suppression (Soft-NMS) to improve localization performance. The proposed framework is trained and evaluated on public and private datasets that span from scientific documents to various electronic components. Our test results show that the precision of tabular detection can be improved by 1.2% while achieving the same recall as other state-of-the-art models on the public ICDAR2013 dataset. Furthermore, a large improvement in precision has been achieved at extremely high intersection over union (IoU) thresholds (i.e. 95%). Thus, 10.9% higher precision is achieved at 95% IoU for ICDAR2013. For another public dataset, namely ICDAR2017, 8.4% higher precision is achieved at 95% IoU .

Mobile Crowdsensing (MCS) leverages Sensing as a Service paradigm to contribute to the Internet of Things ecosystems through non-dedicated sensing capabilities of smart mobile devices. Distributed and non-trusted nature of MCS systems are vulnerable against various threats for the devices, MCS platforms, as well as the participating devices that provide sensory data services. Out of the many threats, submission of fake tasks may lead to drained resources at the participating devices, and clogged sensing server resources at MCS platforms. In this paper, classical machine learning (ML) performance is boosted by knowledge-based methods and sequential feature selection which is proposed for the first time against fake tasks submission to MCS platforms. Prior Knowledge Input and Prior Knowledge Input with Difference exploit AdaBoost and Decision Tree methods as initial accuracy to improve the accuracy of learning the legitimacy of submitted tasks to MCS platforms. Moreover, Sequential Feature Selection is implemented to investigate further improvements for the detection of task legitimacy in MCS campaigns. Intelligently selected 5 features amongst 10 possible features and implementation of knowledge-based methods boost the accuracy of machine learning performance from 93.67% to 97.37% for AdaBoost, and from 92.28% to 97.58% for Decision Trees.

The advent of Mobile crowdsensing (MCS) facilitates the adoption of ubiquitous sensing solutions in smart environments. Despite its benefits, MCS calls for proper security and trust solutions. Various threatening attacks, such as injection attacks, can compromise both the veracity and integrity of crowdsensed data. This work leverages adversarial machine learning to introduce a smart injection attacker model (SINAM) that may be used in the design of security solutions against injection attacks in MCS. SINAM has been validated during an authentic MCS campaign. Unlike most random data injection models, SINAM monitors data traffic in an online- learning manner, successfully injecting malicious data across multiple victims with near-perfect accuracy rates of 99%. SINAM uses accomplices within the sensing campaign to predict accurate injections based on both behavioral analysis and context similarities.

Clogging attacks in mobile crowdsensing (MCS) denote injection of fake sensing tasks into MCS campaigns in order to interfere with service ability and user participation in sensing campaigns. Due to the lack of a realistic location-based and energy-oriented clogging attack model in MCS, this type of attacks have not been well investigated. To this end, for the first time, we introduce a self organizing feature map (SOFM)-based clogging attack model that aims at maximizing the number of affected participants according to the location of attack zones. These zones are identified by clustering 2-D coordinates of all potential participants and finding out aggregation areas of their mobile devices. We evaluate and verify the introduced attack model via simulations by comparing it to an attack model that relies on random mobility of illegitimate tasks over the attack zones. Our simulation results demonstrate that SOFM-based modeling of clogging attacks in MCS results in a significant impact with almost 50% affected participant population, 24% affected recruitment decisions, and up to 28% energy overhead introduced by illegitimate tasks injected to the MCS campaigns.

Smart grids require high reliability and sufficient bandwidth from wireless networks to support critical real-time applications and massive smart microgrid data. In general, smart microgrids need to guarantee delays at the order of a few μs for highly delay-sensitive data delivery; as well as delays within few seconds for regular data delivery. This paper presents a framework and its performance analysis for microgrid data aggregation where the microgrid is served by a wireless heterogeneous network. Using unsupervised machine learning, the framework introduces a multi-class and delay sensitivity-aware aggregation of microgrid data within the small cells of the heterogeneous network to ensure that clustering reduces the processing time for highly delay-sensitive messages. Thus, at each Transmission Time Interval (TTI), if there is queued delay-sensitive data, they are dequeued ahead of the delay-tolerant data at the scheduler. Through simulations, we show that the proposed approach successfully reduces the queuing delay by 93% for the packets of delay-sensitive (urgent) messages and the Packet Loss Rate (PLR) by 7% when compared to the benchmark where no aggregation mechanism exists prior to the small cell base stations.

Wireless sensor and actuator networks are widely adopted in various applications such as critical infrastructure monitoring where sensory data in big volumes and velocity are prone to security vulnerabilities for the network and the monitored infrastructure. Despite the vulnerabilities of the big data phenomenon, intelligent data analytics technique can enable the analysis of huge amount of data and identification of intrusive behavior in real time. The main performance targets for any Intrusion Detection System (IDS) involve accuracy, detection, precision, F1 score and Receiver Operating Characteristics. Pursuant to these, this paper proposes a big data-driven IDS approach in Wireless Sensor Networks by harnessing reinforcement learning techniques on a hybrid IDS framework. We study the performance of RL-IDS and compare it to the previously proposed Adaptive Machine Learning-based IDS (AML-IDS) namely the Adaptively Supervised and Clustered Hybrid IDS (ASCH-IDS). The experimental results show that RL-IDS can achieve ≈ 100% success in detection, accuracy and precisionrecall rates whereas its predecessor ASCH-IDS performs with an accuracy level that is slightly above 99%.

Mobile Crowd-Sensing and Fog Computing are fundamental Internet of Things technologies tailored for smart cities. The former enables user's devices to collect and share data in urban environments. The latter shifts the computation close to end users, lightening the work that their devices have to perform to communicate sensed data in the Cloud. In a fog-based MCS campaign a large number of devices with heterogeneous resources executes sensing tasks generally distributed by remote servers. A careful selection of some of these users' devices for sensing operations can bring benefits to the whole platform in terms of computational costs and energy saving. In this paper, we propose a novel users' recruitment model based on distance, computational capacity, and residual battery of devices. The selection process is carried out in a scenario where devices of the MCS campaign periodically share their battery and Central Processing Unit status to fog nodes through their short-range communication interfaces. Based on this information, fog nodes select devices suitable for performing specific tasks. To verify the effectiveness of the proposed model, we compare our solution with a selection model based only on distances, using an MCS simulator suitably modified for fog-based scenarios as testbed. Results show that our model is able to achieve a more accurate task resolution and a more effective recruitment selection, detecting those devices that can perform sensing operations better than others, thus, guaranteeing an overall average saving of computational and energy resources.

Mobile crowd-sensing (MCS) has gained significant momentum in recent years for sensory data acquisition through non-dedicated sensors. Even though most of the participants are assumed to be willing to participate in the sensing campaigns, some smartphone users may be reluctant to grant access to particular sensors in their devices. Besides this, the presence of adversaries in the participant pool makes the participant selection problem further challenging. With these in mind, we introduce Reputation and Comfort Level Aware Participant Selection (RACLAPS)which allows participants to modify their available set of sensors that can be accessed by central platform/task publisher i.e. participants can turn-off sensors according to their comfort. To demonstrate the effect of RA-CLAPS, we utilize Selective and Reputation-aware Recruitment (SRR) in which participants are selective in choosing their task to sense solely to improve income. To enrich the discussion, Non-Selective and Reputation-aware Recruitment (NSR) is also considered in which participants are given no choice regarding selectiveness, sensor configuration. Simulation results show that RA-CLAPS improves average user utility by 7.6% compared to its predecessor, SRR. We also mention that average discomfort per participant is reduced by 6.4% under RA-CLAPS when compared to non-selective and selective recruitment approaches.

With the growth of information flow through supply chains, we address the issue of semantically segmenting tabular data from document flows. This challenge is abstract in definition as there is no guideline to what defines a table, therefore we primarily applied deep learning methods to compare performances, as well as a morphology-based method to compare several methods for the task of table structure detection. Taking advantage of transfer learning, we found that Mask-RCNN was the most capable network at abstracting to segmentation of tables. Due to the large variation in sizes between columns and rows, most networks failed to detect both with equal effectiveness. However with Mask-RCNN 97.01% precision and 98.28% recall were attained, which put it far ahead of other models in row detection, cementing Mask-RCNN as the most effective choice in this task.

The global electronic components supply chain consists of tens of thousands of e-component manufacturers who fabricate over a billion distinct components. These are described in datasheets that differ in style, layout and content, and frequently publish the salient product information in tables. Keeping up-to-date on this information consumes a great deal of human effort and corporate resources. Based on the motivation that AI-based techniques are strong candidates to minimize human intervention in many applications, in this paper, we aim at the first stage of this problem and conduct a comparison of deep learning methods in detecting tabular elements in these documents. Deep learning-based object detectors are shown to be state of the art in detection tasks in different domains therefore we chose two cutting-edge models to adapt to this field, namely Faster-RCNN and RetinaNet. We use backbone networks which are pre-trained on visually salient datasets then employ transfer learning techniques to adapt to our domain. We compare the two networks under two different datasets, namely a dataset that is widely used in academic studies and a private dataset that is used by the suppliers in real supply chains. Our numerical results show that the two networks adapt well to the domain with Faster-RCNN exhibiting marginally better precision with more than 1% difference. However, RetinaNet stands out with promising recall values indicating Feature Pyramid Network architecture can potentially detect technical documents better.

The papers in this special section focus on mobile cloud computing. The papers address variety of interesting topics covering different aspects of the Mobile Cloud, such as process offloading, work sharing, performance enhancement of Mobile Clouds, security issues in Mobile Clouds, and applications of Mobile Clouds.

Localization is a fundamental function in cooperative control of micro unmanned aerial vehicles (UAVs), but is easily affected by flip ambiguities because of measurement errors and flying motions. This study proposes a localization method that can avoid the occurrence of flip ambiguities in bounded distance measurement errors and constrained flying motions; to demonstrate its efficacy, the method is implemented on bilateration and trilateration. For bilateration, an improved bi-boundary model based on the unit disk graph model is created to compensate for the shortage of distance constraints, and two boundaries are estimated as the communication range constraint. The characteristic of the intersections of the communication range and distance constraints is studied to present a unique localization criterion which can avoid the occurrence of flip ambiguities. Similarly, for trilateration, another unique localization criterion for avoiding flip ambiguities is proposed according to the characteristic of the intersections of three distance constraints. The theoretical proof shows that these proposed criteria are correct. A localization algorithm is constructed based on these two criteria. The algorithm is validated using simulations for different scenarios and parameters, and the proposed method is shown to provide excellent localization performance in terms of average estimated error. Our code can be found at: https://github.com/QingbeiGuo/AFALA.git.

This paper proposes a new framework for GPS-less identification of location of public transportation vehicles by using machine intelligence algorithms by exploiting the vehicular crowd-sensing concept. Since data trustworthiness is vital when data is crowd- solicited via various non-dedicated sensors, assessment and quantification of the trustworthiness of participating sensors plays a key role in the accuracy of the acquired information. To this end, we propose two trustworthiness-aware recruitment schemes for the non-dedicated sensors in a vehicular crowd-sensing environment: Reliability-driven naive recruitment (RDNR) and Reliability-driven exclusive recruitment (RDER). The former determines to use the data of a mobile device with a probability equal to the reliability of the device whereas the latter excludes the participating devices whose reliability scores are below a certain threshold. The data acquired from the recruited participant pool then undergoes an unsupervised machine learning module that is hosted in the cloud. We evaluate the performance of RDNR and RDER in comparison to each other and a non-restrictive recruitment mechanism which does not consider reliability of participants at all. Through simulations, we show that over 85% and 98% accuracy can be achieved in the worst and best cases, respectively while consuming less energy than GPS-based localization approaches.

The Internet of Things (IoT) data can be acquired in crowd-solicited manner, which is based on sensory data acquisition through users of data- enabled devices. Widely known as Mobile Crowd- Sensing (MCS), this method is a user-driven paradigm which facilitates multi-sensory data acquisition through built-in sensors of mobile devices. Despite its benefits, MCS-based services may suffer from low trustworthiness of acquired data. Another issue is the reliability of collected data as there is a risk of intentional tampering or falsified sensor readings. Furthermore, MCS-based services seek innovative methods to influence users' intention to participate in sensing campaigns. Since the effectiveness of MCS relies on the value of the crowd-sensed data, it is crucial to ensure that participants provide trustworthy sensory data. In this paper, we propose Trustworthiness-Aware Coalitional Recruitment of Crowd-Sensors (TA- CROCS), a coalitional game-based user recruitment and incentive solution to improve participation of truthful users by increasing their payoff as well as respecting the privacy of smartphone users during the sensing campaigns. Through simulations, we show that in the presence of malicious users, reputation-aware and coalitional game-based recruitment outperforms collaborative reputation- based crowd-sensor selection by up to 25% in terms of platform utility and up to 10% in terms of user utility.

This paper proposes a new framework for emulating the functionality of a sensor by using multiple available soft sensors and machine intelligence algorithms. As a case study, the localization of city buses in a smart city setting is investigated by using the accelerometer and microphones of the passengers and a Support Vector Machine (SVM) running in the cloud; in this application, the GPS functionality is emulated by using these two soft sensors. What makes such an emulation feasible is the statistical dependence of the location data (which would normally be obtained from a GPS) on the accelerometer and microphone data; while accelerometers capture data that relate to the typical stop/start patterns of the buses, microphone capture enter/exit patterns of the passengers through the sound levels inside the bus. We evaluate our proposed scheme through simulations and show that the proposed framework can operate with more than 90% accuracy in estimating the location of public buses while preserving the actual location privacy of the smartphone users. This approach results in smartphone battery energy savings of 38-46% (as compared to GPS-based approaches) due to the elimination of the power-hungry GPS devices.

Wireless sensor networks have become integral components of the monitoring systems for critical infrastructures such as the power grid or residential microgrids. Therefore, implementation of robust Intrusion Detection Systems (IDS) at the sensory data aggregation stage has become of paramount importance. Key performance targets for IDS in these environments involve accuracy, precision, and the receiver operating characteristics which is a function of the sensitivity and the ratio of false alarms. Furthermore, the interplay between machine learning and networked systems has led to promising opportunities, particularly for the system level security of wireless sensor networks. Pursuant to these, in this paper, we propose Adaptively Supervised and Clustered Hybrid IDS (ASCH-IDS) for wirelessly connected sensor clusters that monitor critical infrastructures. The proposed ASCH-IDS mechanism is built on a hybrid IDS framework, and transforms the previous work by continuously monitoring the behavior of the receiver operating characteristics, and adaptively directing the incoming packets at a sensor cluster towards either misuse detection or anomaly detection module. We evaluate the proposed mechanism by introducing real attack data sets into simulations, and show that our proposal performs at 98.9% detection rate and approximately 99.80% overall accuracy to detect known and unknown malicious behavior in the sensor network.

Consolidation of Internet of Things and Fog computing paradigms requires effective and efficient application-layer protocols between service seekers and providers. As most of these nodes run on batteries, discovering service providing devices in an IoT-Fog environment has to be performed in an energy-efficient way. In this paper, we propose Power Efficient Node Discovery (PEND), which is an MQTT-driven IoT-fog integration solution for the sustainability of object discovery in a publish/subscribe environment. By enabling the MQTT broker to serve as a fog node to trigger turning on/off of the Bluetooth interfaces of subscriber objects, Bluetooth Low Energy Scanner (BLE-S), and to monitor the trajectories of publishers/advertisers, Bluetooth low Energy Advertiser (BLE-A), we introduce significant reduction in the Bluetooth, CPU, and process- specific power consumption of the mobile devices. The reduction in the battery drain by the BLE interface under the proposed scheme can be as low as 10%-20% of a naive, locality based discovery benchmark whereas the process specific battery drain of the proposed scheme can be as low as 55%-62% of the node discovery benchmark. Furthermore, with the synchronization of the publishers and subscribers at the fog layer entity, i.e., MQTT broker, 100% node discovery can be achieved by the scanning/service subscriber devices.

The pervasiveness of smartphones equipped with various built-in sensors combined with the capability of serving multiple applications that could access social network information introduces next generation soft biometrics tools that could be used to verify a user's identity through their social behavior. Smart mobile devices can provide multi-modal data acquisition from various social networking applications, and when aggregated, these data can help form highly identifiable behaviometric information. Continuous identification and authentication of users through monitoring social behavior improves detection of identity spoofing. In this paper, we propose a social behaviometric framework to cope with identity spoofing on smartphones. The proposed framework consists of a front-end client module that acquires and provides social networking data to the back-end module which runs online machine learning procedures and provides analytics as a service to the front-end in order to verify user identity through social interactions. We evaluate the performance of the proposed framework by using real data collected from participants, and inject noisy behavioral patterns to simulate identity spoofing scenarios. Performance results show that under anomalous behavioral patterns, the proposed system can identify genuine users with up to 97% success ratio using an aggregated behavior pattern on five different social network applications.

Wireless Sensor Networks (WSNs) have been widely adopted to monitor various ambient conditions including critical infrastructures. Since power grid is considered as a critical infrastructure, and the smart grid has appeared as a viable technology to introduce more reliability, efficiency, controllability, and safety to the traditional power grid, WSNs have been envisioned as potential tools to monitor the smart grid. The motivation behind smart grid monitoring is to improve its emergency preparedness and resilience. Despite their effectiveness in monitoring critical infrastructures, WSNs also introduce various security vulnerabilities due to their open nature and unreliable wireless links. In this paper, we focus on the, Black-Hole (B-H) attack. To cope with this, we propose a hierarchical trust-based WSN monitoring model for the smart grid equipment in order to detect the B-H attacks. Malicious nodes have been detected by testing the trade-off between trust and dropped packet ratios for each Cluster Head (CH). We select different thresholds for the Packets Dropped Ratio (PDR) in order to test the network behaviour with them. We set four different thresholds (20%, 30%, 40%, and 50%). Threshold of 50% has been shown to reach the system stability in early periods with the least number of re-clustering operations.

As vehicles get smarter, with supplementary onboard gear providing advanced applications and provisioning services related to traffic management, the requirement for simple and effective access to information has grown extensively. The new applications manage more complex operations and, unlike other mobile devices, mobile vehicle devices provide location based services, real-time functionality, provisioning services and storage, all without the shortcomings of traditional mobile devices. Vehicular cloud computing can perform a broad set of on-demand services and applications, which make this method highly applicable to urban settings. Provisioning services often encounter unexpected interruptions that increase provisioning latency and service usage duration, ultimately leading to higher charges for the driver. This paper advances our previously proposed distributed model to handle service management in vehicular clouds, by using the concept of Vehicular Trusted Third Party (VTTP) with different type of provisioning services. This model has the capability to switch between TTPs, which allows drivers to exploit the benefits of different existing services, and connect to the TTP that best meets their specific requirements. Two new service latency modes are proposed and evaluated: Service Latency Sensitive Mode (SLSM) and Neutral mode. The proposed model has been implemented and evaluated using simulations of real-time light and heavy duty services, and various simulation scenarios show that using a VTTP can significantly help drivers reduce their service latency (~30%) and costs (~26%).

Monitoring the Smart Grid (SG) is highly desired for critical applications such as power quality assessment and transformer monitoring. Due to their low-cost, flexibility and efficiency as well as their widely usage in several critical infrastructure monitoring applications, Wireless Sensor Networks (WSNs) are estimated to be extensively used in SG applications. WSNs-based SG networks are vulnerable to different types of attacks and intruders. In order to operate networks in secured environments, in this paper we analyze our Clustered Hierarchal Hybrid-Intrusion Detection System (CHH-IDS) that is responsible for various attacks injected by known and unknown intruders. As False Positives (FPs) and False Negatives (FNs) are the key performance parameters in IDS, we investigate mitigation of FNs through a two-tier intrusion detection approach, which deals with anomaly and signature detection in parallel. In the presence of such a hybrid mode, utilization proportion between the anomaly detection and signature detection models affect the FN performance. In these two subsystems, Random Forest method is used for signature detection over known attacks and E-DBSCAN (Enhanced Density-Based Spatial Clustering of Applications with Noise) method is used for anomaly detection over unknown attacks. Through simulations that run on real datasets, we validate that the higher the weight of anomaly detection subsystem (i.e. the lower the weight of the signature detection subsystem), the lower the FN rates experienced by the entire H-IDS system. More specifically, we show that FN rates can be significantly reduced by 20.4% when the weight on anomaly detection subsystem is increased from 60% to 70% while the accuracy is expected to be improved through signature detection subsystem by using the Random Forest which has higher detection rate than the E-DBSCAN method.

The Smart City vision is to improve quality of life and efficiency of urban operations and services while meeting economic, social, and environmental needs of its dwellers. Realizing this vision requires cities to make significant investments in all kinds of smart objects. Recently, the concept of smart vehicle has also emerged as a viable solution for various pressing problems such as traffic management, drivers' comfort, road safety and on-demand provisioning services. With the availability of onboard vehicular services, these vehicles will be a constructive key enabler of smart cities. Smart vehicles are capable of sharing and storing digital content, sensing and monitoring its surroundings, and mobilizing on-demand services. However, the provisioning of these services is challenging due to different ownerships, costs, demand levels, and rewards. In this paper, we present the concept of Smart Vehicle as a Service (SVaaS) to provide continuous vehicular services in smart cities. The solution relies on a location prediction mechanism to determine a vehicle's future location. Once a vehicle's predicted location is determined, a Quality of Experience (QoE) based service selection mechanism is used to select services that are needed before the vehicle's arrival. We provide simulation results to show that our approach can adequately establish vehicular services in a timely and efficient manner. It also shows that the number of utilized services have been doubled when prediction and service discovery is applied.

Recent works have sought to improve network performance by employing Multipath Transmission Control Protocol (MPTCP) to aggregate flows from heterogeneous wireless interfaces in a single connection. Although existing proposals are powerful, coupled congestion control algorithms suffer from high variation in path delays, bandwidth and loss rate, typical issues on heterogeneous wireless networks. Such variations are even higher over concurrent multipath transmissions, and they are enhanced in presence of bufferbloat, i.e. high delays caused by long queues. Hence, to cope with this limitation, we propose a major shift from the Active Queue Management (AQM) concept to Active Stack Management (ASM) concept, namely Controlled Delay ASM (CD-ASM) for HetNets to handle with the dropped packet ratio in the MPTCP congestion control mechanism. Differently from other approaches, CD-ASM gives priority to the most recent packets, being a promising solution. Moreover, we provide a detailed simulation analysis over congestion control algorithms by comparing CD-ASM to CoDel and DropTail schemes. Results indicate that our proposal reduces queue drops, and thus diminishing the impact on congestion control; keeping RTT low and improving in 20% the goodput.

Vehicular cloud computing can perform a broad set of on-demand applications and services, which makes it highly suitable for urban settings. Despite a wide range of benefits to various services and applications by vehicular clouds, there are several issues and challenges that need to be carefully addressed in the context of provisioning services. This paper proposes a cooperative distributed game model to handle service management in vehicular clouds. Under this model, service providers play a cooperative game to maximize their total utility taking into consideration their recourse availability, current load, and total payoff. The proposed game has been implemented and evaluated using simulations with scenarios of light and heavy weight services. The game demonstrates that a cooperative technique leads players to handle higher number of services when compared to a non-cooperative setting. Furthermore, we also show that the proposed game mimics the behaviour of an optimization-based baseline solution. Through various simulation scenarios, we show that the proposed scheme introduces more than 85% similarity to the optimal solution when a few number of players participate, and its similarity to the optimal solution is improved to 99% when the number of the players increases by only 50%.

In recent years, various researches have been conducted in order to find ways to cover a target or groups of targets with priority-based target coverage and sensor deployment mechanisms taking the front seats. However, with these researches, effective target coverage has been a recurrent issue due to various factors like conflict between sensors and excessive waiting time for targets to be covered. In this paper, we proposed an algorithm based on queuing theory in tandem with mobile crowd sensing to tackle these issues. To do this, first, we develop some models which are based on the birth-and-death mechanism (one of the tools in queuing theory) to determine how long a target has to wait, the mean busy period of sensors and mean idle period of sensors. While developing these models, we consider cases where there exist a single sensor and n-sensors in the system. Based on these models, we develop the required algorithm. The simulation result shows that as the number of sensors increases relative to the number of targets, an average time before a target gets discovered is 0.2 s and sensor utilization decreasing toward zero as the number of sensors increases.

With the widespread applications of Internet of Things (IoT), the emergency response performance for large-scale network packets is facing serious challenge, especially for renewable distributed energy resources monitoring in a smart grid. Therefore, how to improve the real-time performance of the emergency data packets has been a critical issue. Traditional packet scheduling schemes and topology optimization strategies are not suitable for a large-scale IoT-based smart grid. To address this problem, this paper proposes a new packet scheduling scheme named LOES, which first combines the priority-based packet scheduling scheme with local optimization. We exchange local geographic information to reduce the hop counts and distance between distributed source nodes and sink nodes. Each destination node determines the packet scheduling sequence according to the received emergency information. Finally, we compare LOES with first come first serve, multilevel scheme, and dynamic multilevel priority packet scheduling scheme using packet loss rate, packet waiting time, and average packet end-to-end delay as metrics. The simulation results show that LOES outperforms these previous scheduling schemes.

Smart cities exploit the most advanced information technologies to improve and add value to existing public services. Having citizens involved in the process through mobile crowdsensing (MCS) augments the capabilities of the platform without enquiring additional costs. In this paper, we propose a novel framework for data acquisition in MCS deployed over a fog computing platform which facilitates a number of key operations including user recruitment and task completion. Proper data acquisition minimizes the monetary expenditure the platform sustains to recruit and compensate users as well as the energy they spend to sense and deliver data. We propose a new user recruitment policy called Distance, Sociability, Energy (DSE). This policy exploits three criteria: (i) spatial distance between users and tasks, (ii) user sociability, which is an estimate of the willingness of users to contribute to sensing tasks, and (iii) remaining battery charge of the devices. Performance evaluation is conducted in a real urban environment for a large number of participants with new metrics assessing the efficiency of recruitment and the accuracy of task completion. Results reveal that the average number of recruited users improves by nearly 20 percent if compared to policies using only spatial distance as selection criterion.

The Internet of Things (IoT) paradigm makes the Internet more pervasive, interconnecting objects of everyday life, and is a promising solution for the development of next-generation services. Smart cities exploit the most advanced information technologies to improve and add value to existing public services. Applying the IoT paradigm to smart cities is fundamental to build sustainable Information and Communication Technology (ICT) platforms. Having citizens involved in the process through mobile crowdsensing (MCS) techniques unleashes potential benefits as MCS augments the capabilities of the platform without additional costs. Recruitment of participants is a key challenge when MCS systems assign sensing tasks to the users. Proper recruitment both minimizes the cost and maximizes the return, such as the number and the accuracy of accomplished tasks. In this paper, we propose a novel user recruitment policy for data acquisition in mobile crowdsensing systems. The policy can be employed in two modes, namely sociability-driven mode and distance-based mode. Sociability stands for the willingness of users in contributing to sensing tasks. %Furthermore, we propose a novel metric to assess the efficiency of any recruitment policy in terms of the number of users contacted and the ones actually recruited. Performance evaluation, conducted in a real urban environment for a large number of participants, reveals the effectiveness of sociability-driven user recruitment as the average number of recruited users improves by at least a factor of two.

The widespread use of mobile technology has accelerated the popularity of social networking services, and has made these services convenient to access. This paper presents a behaviometric mobile application, namely TrackMaison (Track My activity in social networks). TrackMaison keeps track of social network service usage of smartphone users through data usage, location, usage frequency and session duration of five popular social network services. The data collected by the mobile application is presented to the smartphone user and is analyzed to aid in understanding mobile social network service usage. Furthermore, we introduce the social activity rate and sociability factor metrics where the former is a function of a user's relative data usage rate in social network services and the latter is a function of a user's relative session durations in social networks. By using TrackMaison tool, we identify three user behavior types. Those are active user profile, moderately active user profile and low active user profile. Through analysis of real data, we advocate that continuous identification/authentication of mobile device users is possible by using the introduced sociability metrics. We further present a case study on various Instagram user profiles, and show that low active profiles can be identified with negligible false acceptance rates (FAR) whereas a highly active user can be identified with a FAR as low as 3%.

The past few decades have witnessed incredible advances in human health care, owing to the invention of devices such as MRI scanners, which allow physicians to monitor personal health in more detail than was ever previously possible. Such advances have drastically improved diagnostic quality and patient health care. Central to this incredible progress was the uncanny ability of technologists and academics to invent ever more useful tools to help physicians, be it the X-ray machine, CT, or MRI scanner. Whereas the aforementioned past-decades' tools aimed at acquiring personal data, the advent of the Internet-of-Things, vast computational power available in the cloud, and new data analytics algorithms will completely change the way we acquire and process medical data to improve health care going forward. In this paper, we conduct a quantitative feasibility study of a Digital Health (D-Health) system that is aimed at acquiring and processing health data using the emerging Internet-of-Everything paradigm. We specifically investigate the technological feasibility of communication, software, and data privacy aspects.

In the cloud era, data centers consume tremendous power due to their huge computing and storage requirements. Furthermore, allocation and release of resources by numerous cloud customers leads to significant energy consumption at the data centers, which in turn, increases the Operational expenditures (Opex) of the operators. In this article, we combine energy efficiency and Time of Use (ToU)-awareness, and propose a novel virtualization scheme, namely ToU-aware Provisioning (ToUP) for an inter-data center network over an IP over WDM backbone. In ToUP, in addition to the traffic between two backbone nodes, upstream user demands destined to data centers and downstream data center demands originating from many data centers; inter-data center traffic is also considered for workload sharing between the data centers. Initially, we present an MILP formulation to model the optimal behavior of ToUP. Since the inter-data center network needs to be reconfigured in polynomial time, we propose a simulated annealing (SA)-based heuristic. We verify the heuristic by using the MILP solution as the benchmark. We evaluate ToUP under various scenarios, and numerical results confirm that significant Opex savings can be achieved while demands can be provisioned with low energy consumption in the data centers and network equipments.

Crowdsensing has appeared as a viable solution for data gathering in many applications with the advent of three emerging paradigms, namely Internet of Things, cloud computing, and mobile social networks. Built-in sensors in mobile devices can leverage the performance of the IoT applications in terms of energy and communication overhead savings by sending their data to the cloud servers. When crowdsensing is used for critical applications such as disaster/crisis management and/or public safety in the context of a smart city, trustworthiness of the collected data occurs as a crucial concern. In this paper, we propose using social network theory to evaluate trustworthiness of crowdsensed data, as well as the mobile devices that provide sensing services. To this end, we combine centralized reputation- based evaluation with collaborative reputation values based on votes and vote capacities. We model each participant as a node in a social network where nodes are inter-connected through their interaction values. Interaction stands for being assigned common sensing tasks. We evaluate the performance of our proposal through simulations, and show that use of social network theory-based crowdsensing with combined reputation formulation significantly improves the utility of the crowdsensing platform while dramatically reducing the manipulation probability of malicious nodes.

As global healthcare systems transition into the digital era, remote patient health monitoring will be widespread through the use of inexpensive monitoring devices, such as ECG patches, glucose monitors, etc. Once a sensor-concentrator-cloudlet-cloud infrastructure is in place, it is not unrealistic to imagine a scenario where a physician monitors 20-30 patients remotely. Such an infrastructure will revolutionize clinical diagnostics and preventative medicine by allowing the doctors to access long-term and real-time information, which cannot be obtained from short-term in-hospital ECG recordings. While the large amount of sensor data available to a physician is incredibly valuable clinically, it is overwhelming in raw form. In this paper, the data handling aspect of such a long term health monitoring system is studied. Novel ways to record, aggregate, and visualize this flood of sensory data in an intuitive manner are introduced which allow a doctor to review days worth of data in a matter of seconds. This system is one of the first attempts to provide a tool that allows the visualization of long-term monitoring data acquired from multiple sensors.

Intelligent transportation systems aim at the betterment of the transportation in cooperation with the Information and Communication Technologies (ICTs). Besides, cyber-physical solutions have enabled interaction between the physical and computational components of systems. This paper studies the route selection of paramedics by the assistance of a cyber-physical system which consists of vehicular communications, alternate route optimization and user interaction components. To this end, an optimal alternate routing-tree recommendation framework is proposed by adopting the minimum Steiner tree approach. Initially the mathematical model is presented and is solved as a Mixed Integer Linear Programming (MILP) formulation. Then, in order to assure fast and efficient solution, simulated annealing-based alternate routing-tree recommendation is proposed for paramedics. Through simulations, the proposed approach is shown to be capable of guaranteeing alternate route selection for paramedics with low-delay, low-cost and high resilience.

Use ol social network services has been more widespread as mobile social network applications have been developed for smart phones. Besides, smart phone sensing, namely Sensing-as-a-Service (S2aaS) provides the front-edge access to the cloud-centric Internet of Things. S2aaS can provide crowdsourced data for several purposes such as public safety, crowd management and environment monitoring. Trustworthiness of crowdsourced data is an important challenge in S2aaS as maliciously altered data can be misleading for the S2aaS customer. Reputation-aware crowdsourcing schemes can address trustworthiness problem however smart phone users moving based on a social network mobility (SNM) model introduce further challenges. In this paper, we propose reputation-and-SNM-aware crowdsourcing scheme which is based on an auction executed at a cloud platform. The cloud platform aims at maximum utility by estimating users' future locations based on their interactions over the social network service so that efficient user-sensing task matching can be done. Furthermore, past and current reputation of the users are taken into account while recruiting smart phone users for given sensing tasks. Our simulations show that reputation-awareness accompanied with SNM-awareness can significantly increase the platform utility by up to 55%. Furthermore, incorporation of reputation-awareness can degrade disinformation probability by more than 70%.

Cloud computing model can enable provisioning of sensing services through mobile phones, namely Sensing-as-a-Service (S2aaS). In this paper, we study S2aaS over social networking services for crowd management problem where malicious users report false sensor readings leading to severe disinformation at the crowd control platform. To this end, we propose Trustworthy Sensing for Crowd Management (TSCM) which is a reputation-based crowd management scheme over the cloud platform where sensing data is collected from smart phones based on an auction mechanism. TSCM periodically runs an auction in order to assign dynamically arriving sensing task requests to the smart phone users forming a crowd connected through a social network. User bids, task values and user reputation values are taken as the inputs whereas the outputs are the utility of the crowd management platform and the average utility per user while reputation of a user is a function of the accuracy of the sensed data. Through simulations, we show that TSCM significantly improves the platform utility while degrading the ratio of the maliciously crowdsourced task by 75%. Furthermore, we also show that under TSCM, reputation of malicious users converge to a low value at the order of 40% following a few auctions.

In the Internet of Things (IoT) era, smart devices that are equipped with various types of sensors can enable access to the IoT architecture through a cloud-inspired service model, namely Sensing-as-a-Service (S2aaS). S2aaS can provide crowdsourced data to an application running on a cloud platform. The crowdsourced data can be used for several purposes such as public safety. One of the biggest challenges here is the incentive mechanisms for the users who are requested to provide S2aaS. In this paper, we propose mobility-aware trustworthy crowdsourcing (MATCS) framework in a cloud-centric IoT architecture which adopts and extends a previous scheme, Trustworthy Sensing for Crowd Management (TSCM) [1] by incorporating user mobility-awareness in the presence of maliciously altered sensing data. MATCS employs a user-centric incentive mechanism which collects sensing data based on an auction procedure. In the auction procedure, MATCS uses users' reputations, bids, current location and their estimated dislocation during crowdsourcing process. Furthermore, in order to investigate the benefits of reputation-awareness, we also propose reputation-unaware Mobility-Aware Crowdsourcing (MACS). Performance of MATCS is evaluated via simulations, and it is compared to MACS and a benchmark scheme, which aims at making a compromise between the utilities of the users and the platform by considering neither mobility nor trustworthiness. Simulation results confirm that mobility-awareness improves the utility of the platform significantly whereas combining reputation-awareness and mobility-awareness by MATCS can triple the improvement. Besides, user incomes are not significantly impacted by MACS or MATCS when users are mobile. Furthermore, maliciously altered data ratio can be degraded by 20%~55% by reputation-awareness in MATCS.

In this paper, we present a new protocol for EPC discovery services, namely Delay Tolerant EPC-BGP (DT-EPC-BGP), which is an extension of the previously proposed EPC-BGP. By inheriting all features of EPC-BGP features, DT-EPC-BGP introduces a new mechanism that allows information about the status of the mesh nodes to be exchanged along with other routing information. This new extension sets update sessions with only active nodes, and drops any update request that is destined to an inactive node. We have evaluated DT-EPC-BGP in terms of blocking probability, similarities among routing tables and number of updates in comparison to EPC-BGP. We have shown that DT-EPC-BGP outperforms its predecessor, EPC-BGP by introducing lower blocking probability, lower inconsistency in routing tables among different nodes, and lower number of updates which leads to less control overhead messages.

Vehicular clouds are formed by incorporating cloud-based services into vehicular ad hoc networks. Amongst the several challenges in a vehicular cloud network, virtual machine migration (VMM) may be one of the most crucial issues that need addressing. In this paper, a novel solution for VMM in a vehicular cloud is presented. The vehicular cloud is modeled as a small corporate data center with mobile hosts, equipped with limited computational and storage capacities. The proposed scheme is called Vehicular Virtual Machine Migration (VVMM). The VVMM aims to achieve efficient handling of frequent changes in the data center topology, host heterogeneity, all while doing so with minimum Roadside Unit (RU) intervention. Three modes of VVMM are studied. The first mode, VVMM-U uniformly selects the destinations for VM migrations, which will take place shortly prior to a vehicle's departure from the coverage of the RU. The second mode, VVMM-LW aims at migrating the VM to the vehicle with the least workload, and the third mode, VVMM-MA incorporates mobility awareness by migrating the VM to the vehicle with the least workload and forecasted to be within the geographic boundaries of the vehicular cloud. We evaluate the performance of our proposed framework through simulations. Simulation results show that VVMM-MA introduces significant reduction in unsuccessful migration attempts and results in an increased fairness in vehicle capacity utilization across the vehicular cloud system.

The Internet of Things (IoT) paradigm stands for virtually interconnected objects that are identifiable and equipped with sensing, computing, and communication capabilities. Implementation of services and applications over the IoT architecture can take benefit of the cloud computing concept. Sensing-as-a-Service (S2aaS) is a cloud-inspired service model which enables access to the IoT. In this paper, we present a framework where IoT can enhance public safety by crowd management via sensing services that are provided by smart phones equipped with various types of sensors. In order to ensure trustworthiness in the presented framework, we propose a reputation-based (S2aaS) scheme, namely, Trustworthy Sensing for Crowd Management (TSCM) for front-end access to the IoT. TSCM collects sensing data based on a cloud model and an auction procedure which selects mobile devices for particular sensing tasks and determines the payments to the users of the mobile devices that provide data. Performance evaluation of TSCM shows that the impact of malicious users in the crowdsourced data can be degraded by 75% while trustworthiness of a malicious user converges to a value below 40% following few auctions. Moreover, we show that TSCM can enhance the utility of the public safety authority up to 85%.

Cloud computing offers the flexibility of accessing to a shared pool of resources based on the pay as you go fashion. Data centers, being the main hosts of cloud services, play the key role in the delivery of cloud services while energy consumption and resiliency are two main drivers of the operational expenses of the operators. In this paper, we consider the interconnection of cloud data centers over a wide area network, namely the US National Backbone, via IP over elastic optical transport medium. Initially, we present a numerical model to analyze the outage probability of various demand types such as down-stream data center, upstream data center and data center-to-data center demands. Then, we propose two provisioning schemes, namely, Minimum Outage Probability Provisioning (Min-OPP) and Resilient Provisioning with Minimum Power Consumption (RPMPC) where the latter is an extension of the former incorporating energy-awareness. Through numerical results, we show that energy-awareness in the resilient design reduces the power consumption in the cloud backbone by approximately 7% when compared to Min-OPP with significantly lower (45%∼97%) outage probabilities for data center demands when compared to a naïve energy-minimized provisioning. Furthermore, RPMPC introduces shorter path delays which are not higher than those introduced by Min-OPP.

Cloud computing is the leading edge concept which combines the advantages of several existing computing concepts for the betterment of the Information and Communication Technology (ICT) business. This new business model aims at moving the services such as software, platform and/or infrastructure to a shared pool of resources which are mainly housed in the data centers. In this paper, we propose a novel virtualization scheme for the cloud network with the objective of provisioning the demands among the data centers in a Time-Of-Use (ToU) pricing-aware manner while ensuring maximum energy savings in the cloud network throughout the day. In addition to the unicast demands between backbone nodes, upstream user demand destined to data centers, and downstream data center demands originating from many data centers, here, we also consider inter-data center traffic in order to enable workload sharing between the data centers. Through numerical results, we show that significant savings in terms of operational expenditures (Opex) can be achieved while demands can be provisioned with less energy consumption in the data centers and network equipments. Furthermore, we show that incorporation of inter-data center workload sharing in ToU-aware provisioning can mitigate the increased propagation delay introduced to the user demands submitted to the cloud.

In this paper, we propose an extended architecture of the EPCglobal network that allows tracking objects. This architecture makes use of the distributed discovery services along with the EPC-BGP to provide detailed information about an object regardless of its location. In the EPCglobal network, each object is assigned an IPv6 address once it leaves the last gateway in the supply chain. The IP address of the last gateway enables backtracking of all the information about this object throughout the supply chain. To this end, EPC status updates are crucial in order to advertise any changes in the EPC into the supply chain. On the other hand, concurrent EPC updates, expired EPC databases and/or limitation of resources may cause blocking of an EPC update request. Therefore, we evaluate our proposed architecture in terms of blocking probability of the EPC update requests. To this end, We define three types of blocking, namely the Justified Update Blocking (JUB), Unjustified Update Acceptance (UUA), and Unjustified Update Blocking (UUB). We investigate the impact of the frequency of update advertisements on the blocking probability. Numerical results confirm the trade-off between blocking probability and communication/computation overhead due to EPC update messages. However, further investigation in terms of the number of advertisements and the distance between the routing tables confirms that advertisement of EPC update messages based on certain thresholds can overcome this trade-off.

Despite its great promises, current Cloud offering is still typically rather static and does not support very dynamic execution patterns. In fact, while dynamic resource allocation is typically required to ensure efficient and effective usage of the Cloud resources, Cloud providers have to deal with complex services, usually treated as black-boxes; hence, the estimation of the maximum number of resources that could improve service execution is a big challenge. This paper proposes and explores a novel automatic service rescaling approach to solve the deployment scaling problem. The proposed scheme, called Dynamic Cloud Infrastructure (DCI), has been designed and verified as a new architecture for the IBM Cloud infrastructure. DCI provides hints useful to understand if a particular service could take full advantage from additional resources enabling automatic discovery of the deployment configuration that jointly addresses high service scalability and low resource consumption. We detail the lessons learnt from the application of the proposed solution in the IBM Smart Bay project and present experimental results that demonstrate our approach as a viable first step toward run-time service scaling.

With the advent of cloud computing, storage and computing functions are migrating to remote resources such as virtual servers and storage systems which are mostly hosted in the data centers. This migration can ensure significant energy savings as utilization of local resources contribute to 40% of the Greenhouse Gas emissions of the Information and Communication Technologies (ICTs). On the other hand, provisioning of the cloud services needs to be handled carefully since energy consumption of the transport network, as well as the energy consumed by the data centers, is expected to increase. We revisit our previously proposed Mixed Integer Linear Programming (MILP) models that are used to reconfigure the cloud network design with look-ahead demand profile. Due to long runtimes of the MILP models in large-scale scenarios, in this paper, we propose two heuristics to reconfigure the cloud network for provisioning the cloud and Internet computing demands. The first heuristic aims to minimize the propagation delay while the second one targets minimizing the power consumption of the data centers and the transport network. We verify the heuristics through simulations where MILP models are used as the benchmarks. Numerical results show that power minimized provisioning can guarantee significant energy savings in the cloud network with less resource consumption. We also present the energy versus delay trade-off and point out possible solutions.

Cloud computing is becoming a leading edge business model by migrating the resources such as software, storage and platform to remote locations in the Internet cloud. Data centers, as the main hosts of these cloud services, receive massive amount of demands and transmit services towards Internet routers, consequently consuming enormous bandwidth in the downstream. Due to high computing power, as well as the cooling power, data centers contribute to a significant amount of the power consumption and the operational expenditures (Opex) of the data center operator. In the Internet backbone where the services are transported between the users and the data centers, IP routers make the dominating portion of the power consumption and Opex associated with the network operator. In this paper, we study the impacts of Time of Use (ToU)-awareness on the Opex and energy-efficiency of the cloud network by introducing a Mixed Integer Linear Programming (MILP)-based design scheme for the cloud backbone, which aims at minimizing the network and data center power consumption. Furthermore, the optimization scheme takes advantage of the varying ToU rates in different locations of the cloud network so that Opex is minimized for the network and data center operators. Numerical results approve that Opex savings through ToU-aware provisioning are at the expense of increased delay per demand. Furthermore, by the end of the day, power-minimized provisioning introduces more savings to the network operator as upstream data center demands are transported towards the data centers at the off-peak locations, which in return leads to higher utilization of network components in longer routes.

Information and Communication Technologies (ICTs) are contributing to a large amount of the global electricity consumption. Due to tremendous increase in the bandwidth demands and utilisation of non-renewable energy resources Greenhouse Gas Emissions are increasing proportionally with the increasing demand. Despite their advantages in terms of computing performance, distributed applications such as computational grids are major factors that increase the traffic volume in the Internet. In this paper, we propose a distributed framework to ensure energy savings in the optical WDM backbone which transport the traffic between nodes and several computational grids based on anycast routing. According to the proposed framework, the backbone nodes go to sleep mode and resume active mode in a distributed manner with the objective of maximum energy savings in the backbone. Each node maintains two thresholds which are adaptively adjusted based on the network performance, and these thresholds play the key role in determining the decision of a node whether to sleep or resume. Numerical results confirm that the proposed framework can ensure significant energy savings in the network when compared to the conventional energy-unaware operation mode. We further show that the adoption of the proposed network framework does not degrade significantly the network performance in terms of average blocking probability and end-to-end delay.

Cloud computing calls for efficient solutions to manage the energy consumption of the transport, process and storage services. Recently, we have shown that energy savings in the cloud network and the data centers are at the expense of increased delay; hence degraded service quality. In this paper we propose a new scheme, Delay and Power Minimized Provisioning (DePoMiP) to address energy versus delay tradeoff in the cloud network. DePoMiP reconfigures the cloud network and provisions the demands by jointly minimizing the energy consumption and propagation delay. Through simulations, we compare DePoMiP to our previously proposed heuristics for delay-minimized provisioning and power-minimized provisioning of the demands. Simulation results show that DePoMiP mimics power-minimized provisioning in terms of power consumption while it provisions the demands with a few microseconds higher propagation delay when compared to delay-minimized provisioning. Furthermore, its low channel utilization in the IP over WDM transport network, as well as its fairness among the nodes in terms of power consumption, makes DePoMiP a promising solution for the problem of energy-efficient reconfiguration of the cloud network.

In the cloud computing era, virtualized data centers are expected to host most of the cloud services such as computation, storage and multimedia applications. Cloud services are expected to be transported over the Internet backbone based on anycast/manycast paradigms between the users and data centers. In this paper, we present an optimization model which aims at reconfiguring the cloud network topology so that the delay of cloud service provisioning is minimized without disrupting the service quality of regular Internet services. We compare the performance of the proposed model to the delay performance of an optimization model which aims at minimizing the operational expenditure of the operator. Through numerical results, we show that the proposed optimization model is capable of assuring minimum delay guarantee for the traffic demands destined to/from the data centers, as well as the traffic demands destined to/from the core nodes of the cloud network. Furthermore, we study the overheads and challenges of delay minimized reconfiguration of the cloud network. Numerical results confirm that minimum delay objective does not introduce significant overhead to the data centers in terms of operational expenditure, namely power consumption. On the other hand, we show that the increase in the power consumption of the network equipment in the cloud backbone arises as an important challenge of the presented optimization model.

Significant portion of the energy consumption of the optical networks is expected to be in the transport segment. Besides its improved bandwidth utilization advantage, multi-granular switching concept further helps rectifying the energy bottleneck problem in the backbone. One of the important challenges faced by the multi-granular optical networks is the optical reach enforcement. In this paper, we compare the multi-granular optical network design to the conventional Wavelength Division Multiplexing (WDM)-based network design by enforcing the optical reach limitation as a design constraint. We introduce the heuristics to solve the Routing and Multi-Granular Path Assignment (RMGPA) problem. Our simulation results show that multi-granular optical network design outperforms the WDM-based network design in terms of Operational Expenditure (Opex) as it significantly reduces the power consumption in the backbone. Furthermore, through simulations, we show that the green multi-granular design is efficient in terms of the Capital Expenditure (Capex) as the network cost is also degraded.

To avoid huge data loss in the last mile of Internet service, Passive Optical Networks (PONs) need to be designed with a high availability guarantee. Because next generation PON includes extending the coverage of optical broadband access networks under the name long-reach PON, availability-guaranteed planning of PONs for long-reach access is required. In this paper, we propose a Mixed Integer Linear Programming (MILP)-based approach, and a heuristic algorithm, for the planning of survivable long-reach passive optical networks. The MILP-based planning model mainly consists of cost and availability constraints, while having the objective of largest possible area coverage. The heuristic is called Locate-ONU-with-Lowest-Availability-Requirement-First (LOWLARF), and it performs a faster search for the nearly optimal locations of Optical Network Units (ONUs), Optical Line Terminal (OLT), and the optical splitter having the same objective and constraints with the MILP model. The proposed heuristic and the MILP model are compared in terms of the solution spaces provided for a small sized problem. The heuristic LOWLARF introduces the advantage of significantly degraded running time, and numerical results indicate that it can provide close results to those of the MILP-based planning. On the other hand, three survivability schemes are compared in terms of deployment cost, availability, and coverage by MILP-based planning and LOWLARF. The evaluation is done by two different availability requirement scenarios. The results show that, under both scenarios, the protection scheme offering a lower bound of 99.999% availability leads to the highest deployment cost while it covers the smallest area. The protection schemes that guarantee 99.99% availability by employing less redundancy can cover a larger area under both scenarios.

Optical WDM networks can be employed as the transport medium technology for cloud computing services since they have high capacity and low delay, and they satisfy the service requirements by the help of the control plane. Recent research has shown that cloud services can be efficiently provisioned based on anycast or manycast paradigms. In this paper, we focus on the energy savings in the optical transport network which forms a communication infrastructure for the cloud services based on the manycast paradigm. We propose an optimization model to maximize the energy savings by putting the wavelength routing modules of the optical nodes in the power saving mode. Based on the optimization model, we propose an evolutionary algorithm, namely the Evolutionary Algorithm for Green Light-tree Establishment (EAGLE) which can provide lower runtime for large topologies and find a suboptimal solution. We evaluate the performance of our optimization model by running EAGLE under a topology lying on four different time zones, i.e., NSFNET. Simulation results verify that selecting a feasible number of nodes to put their wavelength routing modules in the power saving mode leads to significant energy savings in transportation of the cloud services over WDM networks. Furthermore, the proposed scheme does not introduce a resource consumption penalty when compared to the wavelength minimizing approach.

Passive Optical Network (PON) deployments have recently been aiming to combine the capacity of metro and access networks in the last mile of the Internet service provisioning. Deployment of PONs by running fiber to the premises introduces the advantage of huge capacity but at the same time, it calls for a robust design in order to avoid long service outage durations in case of network failures where survivable network design is mostly limited to the deployment budget. In this paper, we propose three mixed integer linear programming (MILP) models for various survivability policies to deploy reliable long-reach PONs under the budget limitations. Each MILP model aims to place the ONUs in optimal locations so that the covered area is maximized while availability requirements of the users are satisfied within the deployment budget. We solve the MILP models under the uniform and heterogeneous availability requirement scenarios and show that service availability and coverage introduce a trade-off so as the coverage and deployment cost do. Two out of the three survivability policies can guarantee 99.99% service availability while the third one is able to guarantee 99.999% by running the proposed MILP models. However, the first two schemes are able to cover larger area when compared to the third scheme which is the most reliable protection policy.

In this paper, we have proposed a dynamic IP address assignment architecture for wireless heterogeneous sensor networks. The assignment scheme and the architecture guarantee that communication channels can be assigned only between the registered devices ensuring the security. The dynamic IP address assignment scheme is based on the advertisement of the IP address utilization status at the base stations. Thus, each base station advertises its IP address utilization database when the ratio of the negative acknowledgement messages received from the DNS exceeds a certain threshold. By simulations, we have shown that the proposed assignment scheme introduces significant enhancement in terms of blocking probability when compared to an approach where each base station has its own IP address pool. Furthermore, we have defined three types of blocking, the real blocking, the unjustified acceptance and the unjustified rejections. We have seen that the proposed scheme can lead to lower blocking probability compared to the uniform IP assignment as long as the update threshold is kept below 1.5%.

In this paper, we propose a bandwidth allocation scheme working with differentiated services for the Multi-Point Control Protocol (MPCP) in Long-Reach Passive Optical Networks. The proposed scheme is an enhancement to our recently proposed bandwidth allocation scheme Periodic Gate Optimization (PGO), and it is called Periodic Gate Optimization with Quality of Service Awareness (PGO-QoS). Long-Reach PON introduces a challenge by the deployment of passive elements in a long distance up to 100km between the OLT and the ONUs. It becomes more challenging when the subscribers have different Service Level Agreements (SLAs) with specific performance requirements such as delay bounds and/or packet drop probabilities. PGO-QoS consists of two independent modules; intra-ONU scheduling and dynamic bandwidth allocation. Intra-ONU scheduling stands for the burstification of the buffered packets at the ONUs, and it determines the proportion of the packets to be dequeued from the buffer of each SLA class. These proportions are also appended to the REPORT message to be used by the OLT in the dynamic bandwidth allocation module. The bandwidth allocation module runs at the OLT. This module is mostly inherited from recently proposed PGO. Based on the collected REPORT messages, the OLT periodically builds an ILP model to estimate the appropriate GATE credits of the overloaded ONUs until the next optimization period. The ILP model sets the appropriate constraints so that the OLT tends to prioritize the ONUs where dequeuing proportions of the high priority queues are greater. The simulation results show that PGO-QoS leads to a lower average delay and shorter queue length and less packet delay. Moreover, the proposed scheme also introduces decreased delay and low packet loss for the higher priority SLA classes which are class-3 and class-2.

Yönlendirme performansıni iyileştiren MPLS teknolojisinin ulaştırma ağlarında giderek artan kullanımı beraberinde detaylı ağ yönetimi, Servis Kalitesi (SK) ve Kaynak Kullanım Optimizasyonu gibi daha ileri seviye isteklerin oluşmasına yol açtı. Generalized Multiprotocol Label Switching (GMPLS) mimarisi çoğunlukla bu istekleri karşılarken, ağ ve bağlantı sürdürülebilirliği halen hesaba katılmak zorundadır. Bu çalısmada, Yedek Kaynak Ataması (YKA) algoritmasına dayanan, kaynakların verimli kullanımını ve Servis Kalite Anlaşmalarında (SKA) belirlenen sürdürülebilirlik seviyesini garanti eden yeni bir bağlantı oluşturma şeması tasarlanmıstır. Ayrıca, bağlantı rededilme olasılığını düşürmek için En Az Yeterli Yol (EAYY) ve Değiştirme Metodu (DM) isminde iki adet sınıf bazlı sezgisel yöntem önerilmiştir. Önerilen optimizasyon tabanlı model ve sezgisel yöntemlerin performansları karsılastırılmıstır. Simulasyon sonuçları göstermistir ki EAYY yöntemi en düsük bağlantı rededilme olasılığını sağlamaktayken YKA tabanlı bağlantı oluşturma yöntemi ve DM yöntemi birbirine benzer bağlantı rededilme değerleri üretmişlerdir. Ayrıca, sezgisel yöntemlerin YKA tabanlı model ile çesitli ağ trafik seviyelerinde karşılastırıldıklarında fazladan kaynak kullanımına yol açmadıkları da gösterilmistir.

In this paper, we propose a planning heuristic called Locate-ONU-with-Lowest-Availability-Requirement-First (LOWLARF) to compare the coverage capability of three previously proposed survivability policies under these constraints. The heuristic is designed to determine the length of the feeder fiber and to locate each ONU on the appropriate location in order to meet the availability requirements while not violating the budget limit. The heuristic is shown to locate the ONUs within the availability requirements and the budget limit. In the test scenarios, ONUs are assumed to contract the users requesting different availability levels while a pre-specified budget limit is set for each scenario. By our proposed planning heuristic, we compare three survivability schemes under various budget constraints and split ratios within various square regions. We show that the better the availability the less the coverage in terms of total deployed fiber length. Furthermore, we also show that better protection leads to a smaller ONU region while less protection allows to cover a larger region by the ONUs.

Fault localization is an important issue in all-optical networks. The Limited Perimeter Vector Matching (LVM) protocol is a novel fault localization protocol for localizing single-link failures in all-optical networks. In this paper, we study the fault localization optimization problem in applying the LVM protocol to static networks, where traffic (or lightpath) demand is known a priori. Given the traffic demand, the fault localization optimization problem is to optimize the traffic distribution so that the fault localization probability in terms of the number of localized links can be maximized. We formulate the problem into an integer linear programming problem and use CPLEX to solve the problem. We show through numerical results that by optimizing the traffic distribution the fault localization probability in terms of the number of localized links can be maximized. Moreover, the solution to the problem can also provide the maximum number of wavelengths needed on each link to obtain the maximum fault localization probability.

In this paper, we propose two availability-aware connection provisioning algorithms, namely global differentiated availability-aware provisioning (G-DAP) and link-by-link differentiated availability-aware provisioning (LBL-DAP) for the connections of differentiated availability classes. G-DAP attempts to provide a global feasible sharing degree for each availability class on all of the wavelengths throughout the network. LBL-DAP provides a feasible sharing degree for each class on the wavelengths of each link separately. We evaluate the performance of the proposed schemes by simulation under NSFNET topology, and compare the results with a reliable connection provisioning scheme. The connections arrive with various availability requirements. We show that G- DAP and LBL-DAP provide an enhanced blocking ratio and resource overbuild globally and for the high priority classes.

In this paper, we present a new connection provisioning algorithm for availability-aware optical transport networks planning regarding shareability of backup channels. The proposed scheme is designed to work under shared backup path protection policy and attempts to minimize the conflict between unavailability per connection and resource overbuild. It is adapted into a conventional two-step availability-constrained connection provisioning scheme. We evaluate the performance of this dynamic shareability driven connection provisioning scheme in terms of unavailability per connection and resource consumption as applied to NSFNET and EON topologies. Simulation results show that dynamic shareability driven connection provisioning scheme reduces the unavailability per connection by not violating the resource consumption as much as the dedicated path protection.

Two loss rate-based optical burst assembly techniques addressing contention resolution are studied. These techniques stem from the burst assembly schemes using adaptive thresholds, which have been introduced earlier by the authors. The loss rates on the links/paths leading to the destination nodes are used to estimate congestion levels. Three alternative time and size threshold value pairs are employed based on the congestion level observed. Here, the aim is to generate short bursts under heavy traffic and long bursts under light traffic conditions in order to enhance performance. The results that are obtained in terms of byte loss rate and delay are compared with those of the hybrid burst assembly. It is observed that the adaptive techniques significantly enhance the byte loss rate as traffic gets heavier while keeping end-to-end delay in a feasible range.